Daily Papers

The rapid expansion of chemistry literature poses significant challenges for researchers seeking to efficiently access domain-specific knowledge. To support advancements in chemistry-focused natural language processing (NLP), we present ChemRxivQuest, a curated dataset of 970 high-quality question-answer (QA) pairs derived from 155 ChemRxiv preprints across 17 subfields of chemistry. Each QA pair is explicitly linked to its source text segment to ensure traceability and contextual accuracy. ChemRxivQuest was constructed using an automated pipeline that combines optical character recognition (OCR), GPT-4o-based QA generation, and a fuzzy matching technique for answer verification. The dataset emphasizes conceptual, mechanistic, applied, and experimental questions, enabling applications in retrieval-based QA systems, search engine development, and fine-tuning of domain-adapted large language models. We analyze the dataset's structure, coverage, and limitations, and outline future directions for expansion and expert validation. ChemRxivQuest provides a foundational resource for chemistry NLP research, education, and tool development.

Large language models show promise for autoformalization, the task of automatically translating natural language into formal languages. However, current autoformalization methods remain limited. The last reported state-of-the-art performance on the ProofNet formalization benchmark for the Lean proof assistant, achieved using Codex for Lean 3, only showed successful formalization of 16.1% of informal statements. Similarly, our evaluation of GPT-4o for Lean 4 only produces successful translations 34.9% of the time. Our analysis shows that the performance of these models is largely limited by their inability to generate formal statements that successfully type-check (i.e., are syntactically correct and consistent with types) - with a whopping 86.6% of GPT-4o errors starting from a type-check failure. In this work, we propose a method to fix this issue through decoding with type-check filtering, where we initially sample a diverse set of candidate formalizations for an informal statement, then use the Lean proof assistant to filter out candidates that do not type-check. Using GPT-4o as a base model, and combining our method with self-consistency, we obtain a +18.3% absolute increase in formalization accuracy, and achieve a new state-of-the-art of 53.2% on ProofNet with Lean 4.

Retrieval-Augmented Generation (RAG) has emerged as a common paradigm to use Large Language Models (LLMs) alongside private and up-to-date knowledge bases. In this work, we address the challenges of using LLM-as-a-Judge when evaluating grounded answers generated by RAG systems. To assess the calibration and discrimination capabilities of judge models, we identify 7 generator failure modes and introduce GroUSE (Grounded QA Unitary Scoring of Evaluators), a meta-evaluation benchmark of 144 unit tests. This benchmark reveals that existing automated RAG evaluation frameworks often overlook important failure modes, even when using GPT-4 as a judge. To improve on the current design of automated RAG evaluation frameworks, we propose a novel pipeline and find that while closed models perform well on GroUSE, state-of-the-art open-source judges do not generalize to our proposed criteria, despite strong correlation with GPT-4's judgement. Our findings suggest that correlation with GPT-4 is an incomplete proxy for the practical performance of judge models and should be supplemented with evaluations on unit tests for precise failure mode detection. We further show that finetuning Llama-3 on GPT-4's reasoning traces significantly boosts its evaluation capabilities, improving upon both correlation with GPT-4's evaluations and calibration on reference situations.

LLMs have long demonstrated remarkable effectiveness in automatic program repair (APR), with OpenAI's ChatGPT being one of the most widely used models in this domain. Through continuous iterations and upgrades of GPT-family models, their performance in fixing bugs has already reached state-of-the-art levels. However, there are few works comparing the effectiveness and variations of different versions of GPT-family models on APR. In this work, inspired by the recent public release of the GPT-o1 models, we conduct the first study to compare the effectiveness of different versions of the GPT-family models in APR. We evaluate the performance of the latest version of the GPT-family models (i.e., O1-preview and O1-mini), GPT-4o, and the historical version of ChatGPT on APR. We conduct an empirical study of the four GPT-family models against other LLMs and APR techniques on the QuixBugs benchmark from multiple evaluation perspectives, including repair success rate, repair cost, response length, and behavior patterns. The results demonstrate that O1's repair capability exceeds that of prior GPT-family models, successfully fixing all 40 bugs in the benchmark. Our work can serve as a foundation for further in-depth exploration of the applications of GPT-family models in APR.

We investigate the potential of GPT-4~gpt4 to perform Neural Architecture Search (NAS) -- the task of designing effective neural architectures. Our proposed approach, GPT-4 Enhanced Neural archItectUre Search (GENIUS), leverages the generative capabilities of GPT-4 as a black-box optimiser to quickly navigate the architecture search space, pinpoint promising candidates, and iteratively refine these candidates to improve performance. We assess GENIUS across several benchmarks, comparing it with existing state-of-the-art NAS techniques to illustrate its effectiveness. Rather than targeting state-of-the-art performance, our objective is to highlight GPT-4's potential to assist research on a challenging technical problem through a simple prompting scheme that requires relatively limited domain expertiseCode available at \href{https://github.com/mingkai-zheng/GENIUS{https://github.com/mingkai-zheng/GENIUS}.}. More broadly, we believe our preliminary results point to future research that harnesses general purpose language models for diverse optimisation tasks. We also highlight important limitations to our study, and note implications for AI safety.

Recent progress in large language models (LLMs) like GPT-4 and PaLM-2 has brought significant advancements in addressing math reasoning problems. In particular, OpenAI's latest version of GPT-4, known as GPT-4 Code Interpreter, shows remarkable performance on challenging math datasets. In this paper, we explore the effect of code on enhancing LLMs' reasoning capability by introducing different constraints on the Code Usage Frequency of GPT-4 Code Interpreter. We found that its success can be largely attributed to its powerful skills in generating and executing code, evaluating the output of code execution, and rectifying its solution when receiving unreasonable outputs. Based on this insight, we propose a novel and effective prompting method, explicit code-based self-verification~(CSV), to further boost the mathematical reasoning potential of GPT-4 Code Interpreter. This method employs a zero-shot prompt on GPT-4 Code Interpreter to encourage it to use code to self-verify its answers. In instances where the verification state registers as ``False'', the model shall automatically amend its solution, analogous to our approach of rectifying errors during a mathematics examination. Furthermore, we recognize that the states of the verification result indicate the confidence of a solution, which can improve the effectiveness of majority voting. With GPT-4 Code Interpreter and CSV, we achieve an impressive zero-shot accuracy on MATH dataset (53.9\% to 84.3\%).

With the Generative Pre-trained Transformer 3.5 (GPT-3.5) exhibiting remarkable reasoning and comprehension abilities in Natural Language Processing (NLP), most Question Answering (QA) research has primarily centered around general QA tasks based on GPT, neglecting the specific challenges posed by Complex Table QA. In this paper, we propose to incorporate GPT-3.5 to address such challenges, in which complex tables are reconstructed into tuples and specific prompt designs are employed for dialogues. Specifically, we encode each cell's hierarchical structure, position information, and content as a tuple. By enhancing the prompt template with an explanatory description of the meaning of each tuple and the logical reasoning process of the task, we effectively improve the hierarchical structure awareness capability of GPT-3.5 to better parse the complex tables. Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets, leading to state-of-the-art (SOTA) performance.

Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with capabilities to self-refine and improve generated code autonomously. However, on challenging coding tasks with extremely large search space, current agentic approaches still struggle with multi-stage planning, generating, and debugging. To address this problem, we propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions. In each stage, critical decision-making (ranking, termination, expanding) of the exploration process is guided by both the environmental execution-based feedback and LLM-agent-generated feedback. We comprehensively evaluated CodeTree on 7 code generation benchmarks and demonstrated the significant performance gains of CodeTree against strong baselines. Using GPT-4o as the base model, we consistently achieved top results of 95.1 on HumanEval, 98.7 on MBPP, and 43.0 on CodeContests. On the challenging SWEBench benchmark, our approach led to significant performance gains.

This paper presents a simple and cost-effective method for synthesizing data to train question-answering systems. For training, fine-tuning GPT models is a common practice in resource-rich languages like English, however, it becomes challenging for non-English languages due to the scarcity of sufficient question-answer (QA) pairs. Existing approaches use question and answer generators trained on human-authored QA pairs, which involves substantial human expenses. In contrast, we use an instruct-tuned model to generate QA pairs in a zero-shot or few-shot manner. We conduct experiments to compare various strategies for obtaining QA pairs from the instruct-tuned model. The results demonstrate that a model trained on our proposed synthetic data achieves comparable performance to a model trained on manually curated datasets, without incurring human costs.

We describe GEMBA, a GPT-based metric for assessment of translation quality, which works both with a reference translation and without. In our evaluation, we focus on zero-shot prompting, comparing four prompt variants in two modes, based on the availability of the reference. We investigate nine versions of GPT models, including ChatGPT and GPT-4. We show that our method for translation quality assessment only works with GPT~3.5 and larger models. Comparing to results from WMT22's Metrics shared task, our method achieves state-of-the-art accuracy in both modes when compared to MQM-based human labels. Our results are valid on the system level for all three WMT22 Metrics shared task language pairs, namely English into German, English into Russian, and Chinese into English. This provides a first glimpse into the usefulness of pre-trained, generative large language models for quality assessment of translations. We publicly release all our code and prompt templates used for the experiments described in this work, as well as all corresponding scoring results, to allow for external validation and reproducibility.

As of September 2023, ChatGPT correctly answers "what is 7+8" with 15, but when asked "7+8=15, True or False" it responds with "False". This inconsistency between generating and validating an answer is prevalent in language models (LMs) and erodes trust. In this paper, we propose a framework for measuring the consistency between generation and validation (which we call generator-validator consistency, or GV-consistency), finding that even GPT-4, a state-of-the-art LM, is GV-consistent only 76% of the time. To improve the consistency of LMs, we propose to finetune on the filtered generator and validator responses that are GV-consistent, and call this approach consistency fine-tuning. We find that this approach improves GV-consistency of Alpaca-30B from 60% to 93%, and the improvement extrapolates to unseen tasks and domains (e.g., GV-consistency for positive style transfers extrapolates to unseen styles like humor). In addition to improving consistency, consistency fine-tuning improves both generator quality and validator accuracy without using any labeled data. Evaluated across 6 tasks, including math questions, knowledge-intensive QA, and instruction following, our method improves the generator quality by 16% and the validator accuracy by 6.3% across all tasks.

Recent studies show that sentence-level extractive QA, i.e., based on Answer Sentence Selection (AS2), is outperformed by Generation-based QA (GenQA) models, which generate answers using the top-k answer sentences ranked by AS2 models (a la retrieval-augmented generation style). In this paper, we propose a novel training paradigm for GenQA using supervision from automatic QA evaluation models (GAVA). Specifically, we propose three strategies to transfer knowledge from these QA evaluation models to a GenQA model: (i) augmenting training data with answers generated by the GenQA model and labelled by GAVA (either statically, before training, or (ii) dynamically, at every training epoch); and (iii) using the GAVA score for weighting the generator loss during the learning of the GenQA model. We evaluate our proposed methods on two academic and one industrial dataset, obtaining a significant improvement in answering accuracy over the previous state of the art.

Code generation models can help improve many common software tasks ranging from code completion to defect prediction. Most of the existing benchmarks for code generation LLMs focus on code authoring or code completion. Surprisingly, there has been far less effort dedicated to benchmarking software testing, despite the strong correlation between well-tested software and effective bug detection. To address this gap, we create and release TestGenEval, a large-scale benchmark to measure test generation performance. Based on SWEBench, TestGenEval comprises 68,647 tests from 1,210 code and test file pairs across 11 well-maintained Python repositories. It covers initial tests authoring, test suite completion, and code coverage improvements. Test authoring simulates the process of a developer writing a test suite from scratch, while test completion mimics the scenario where a developer aims to improve the coverage of an existing test suite. We evaluate several popular models, with sizes ranging from 7B to 405B parameters. Our detailed analysis highlights TestGenEval's contribution to a comprehensive evaluation of test generation performance. In particular, models struggle to generate high-coverage test suites, with the best model, GPT-4o, achieving an average coverage of only 35.2%. This is primarily due to models struggling to reason about execution, and their frequent assertion errors when addressing complex code paths.

Recent advances in generative artificial intelligence (AI) have shown promise in accurately grading open-ended student responses. However, few prior works have explored grading handwritten responses due to a lack of data and the challenge of combining visual and textual information. In this work, we leverage state-of-the-art multi-modal AI models, in particular GPT-4o, to automatically grade handwritten responses to college-level math exams. Using real student responses to questions in a probability theory exam, we evaluate GPT-4o's alignment with ground-truth scores from human graders using various prompting techniques. We find that while providing rubrics improves alignment, the model's overall accuracy is still too low for real-world settings, showing there is significant room for growth in this task.

In this work, we make the first attempt to evaluate LLMs in a more challenging code generation scenario, i.e. class-level code generation. We first manually construct the first class-level code generation benchmark ClassEval of 100 class-level Python code generation tasks with approximately 500 person-hours. Based on it, we then perform the first study of 11 state-of-the-art LLMs on class-level code generation. Based on our results, we have the following main findings. First, we find that all existing LLMs show much worse performance on class-level code generation compared to on standalone method-level code generation benchmarks like HumanEval; and the method-level coding ability cannot equivalently reflect the class-level coding ability among LLMs. Second, we find that GPT-4 and GPT-3.5 still exhibit dominate superior than other LLMs on class-level code generation, and the second-tier models includes Instruct-Starcoder, Instruct-Codegen, and Wizardcoder with very similar performance. Third, we find that generating the entire class all at once (i.e. holistic generation strategy) is the best generation strategy only for GPT-4 and GPT-3.5, while method-by-method generation (i.e. incremental and compositional) is better strategies for the other models with limited ability of understanding long instructions and utilizing the middle information. Lastly, we find the limited model ability of generating method-dependent code and discuss the frequent error types in generated classes. Our benchmark is available at https://github.com/FudanSELab/ClassEval.

Much is promised in relation to AI-supported software development. However, there has been limited evaluation effort in the research domain aimed at validating the true utility of such techniques, especially when compared to human coding outputs. We bridge this gap, where a benchmark dataset comprising 72 distinct software engineering tasks is used to compare the effectiveness of large language models (LLMs) and human programmers in producing Python software code. GPT-4 is used as a representative LLM, where for the code generated by humans and this LLM, we evaluate code quality and adherence to Python coding standards, code security and vulnerabilities, code complexity and functional correctness. We use various static analysis benchmarks, including Pylint, Radon, Bandit and test cases. Among the notable outcomes, results show that human-generated code recorded higher ratings for adhering to coding standards than GPT-4. We observe security flaws in code generated by both humans and GPT-4, however, code generated by humans shows a greater variety of problems, but GPT-4 code included more severe outliers. Our results show that although GPT-4 is capable of producing coding solutions, it frequently produces more complex code that may need more reworking to ensure maintainability. On the contrary however, our outcomes show that a higher number of test cases passed for code generated by GPT-4 across a range of tasks than code that was generated by humans. That said, GPT-4 frequently struggles with complex problem-solving that involve in-depth domain knowledge. This study highlights the potential utility of LLMs for supporting software development, however, tasks requiring comprehensive, innovative or unconventional solutions, and careful debugging and error correction seem to be better developed by human programmers. We plot an agenda for the software engineering community.

Recent advancements in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. Although these models have shown promising results in tasks such as machine translation and summarization, their applicability in code generation tasks remains limited without human involvement. The complexity of programming concepts required for such tasks makes it difficult to develop evaluation metrics that align with human judgment. Token-matching-based metrics, such as BLEU, have demonstrated weak correlations with human practitioners in code generation tasks. Moreover, the utilization of human-written test suites to evaluate functional correctness can be challenging in domains with low resources. To overcome these obstacles, we propose a new evaluation framework based on the GPT-3.5 (GPT-3.5-turbo), for code generation assessments. Our framework addresses the limitations of existing approaches by achieving superior correlations with functional correctness and human preferences, without the need for test oracles or references. We evaluate the efficacy of our framework on two different tasks and four programming languages, comparing its performance with the state-of-the-art CodeBERTScore metric, which relies on a pre-trained model. Our results demonstrate that our framework surpasses CodeBERTScore, delivering high levels of accuracy and consistency across various programming languages and tasks. We also make our evaluation framework and datasets available to the public at https://github.com/terryyz/llm-code-eval, encouraging further research in the evaluation of code generation.

Long-form generation is crucial for academic writing papers and repo-level code generation. Despite this, current models, including GPT-4o, still exhibit unsatisfactory performance. Existing methods that utilize preference learning with outcome supervision often fail to provide detailed feedback for extended contexts. This shortcoming can lead to content that does not fully satisfy query requirements, resulting in issues like length deviations, and diminished quality. In this paper, we propose enhancing long-form generation by incorporating process supervision. We employ Monte Carlo Tree Search to gather stepwise preference pairs, utilizing a global memory pool to maintain consistency. To address the issue of suboptimal candidate selection, we integrate external critiques to refine and improve the quality of the preference pairs. Finally, we apply step-level DPO using the collected stepwise preference pairs. Experimental results show that our method improves length and quality on long-form generation benchmarks, with almost lossless performance on general benchmarks across various model backbones.

In this work, we address question answering (QA) over a hybrid of tabular and textual data that are very common content on the Web (e.g. SEC filings), where discrete reasoning capabilities are often required. Recently, large language models (LLMs) like GPT-4 have demonstrated strong multi-step reasoning capabilities. We then consider harnessing the amazing power of LLMs to solve our task. We abstract a Step-wise Pipeline for tabular and textual QA, which consists of three key steps, including Extractor, Reasoner and Executor, and initially design an instruction to instantiate the pipeline and validate that GPT-4 outperforms all existing methods. However, utilizing an online LLM like GPT-4 holds various challenges in terms of cost, latency, and data security risk, which motivates us to specialize smaller LLMs in this task. We develop a TAT-LLM language model by fine-tuning LLaMA 2 with the training data generated automatically from existing expert-annotated datasets following the Step-wise Pipeline. The experimental results have verified that our TAT-LLM model can outperform all baseline models, including the previous best fine-tuned models and very large-scale LLMs like GPT-4 on FinQA, TAT-QA and TAT-DQA benchmarks. We hope our work can serve as a pioneering example of specializing smaller language models for specific tasks.

We introduce Synthetic Alignment data Generation for Safety Evaluation and Red Teaming (SAGE-RT or SAGE) a novel pipeline for generating synthetic alignment and red-teaming data. Existing methods fall short in creating nuanced and diverse datasets, providing necessary control over the data generation and validation processes, or require large amount of manually generated seed data. SAGE addresses these limitations by using a detailed taxonomy to produce safety-alignment and red-teaming data across a wide range of topics. We generated 51,000 diverse and in-depth prompt-response pairs, encompassing over 1,500 topics of harmfulness and covering variations of the most frequent types of jailbreaking prompts faced by large language models (LLMs). We show that the red-teaming data generated through SAGE jailbreaks state-of-the-art LLMs in more than 27 out of 32 sub-categories, and in more than 58 out of 279 leaf-categories (sub-sub categories). The attack success rate for GPT-4o, GPT-3.5-turbo is 100% over the sub-categories of harmfulness. Our approach avoids the pitfalls of synthetic safety-training data generation such as mode collapse and lack of nuance in the generation pipeline by ensuring a detailed coverage of harmful topics using iterative expansion of the topics and conditioning the outputs on the generated raw-text. This method can be used to generate red-teaming and alignment data for LLM Safety completely synthetically to make LLMs safer or for red-teaming the models over a diverse range of topics.

LLM-based agents have demonstrated great potential in generating and managing code within complex codebases. In this paper, we introduce WebGen-Bench, a novel benchmark designed to measure an LLM-based agent's ability to create multi-file website codebases from scratch. It contains diverse instructions for website generation, created through the combined efforts of human annotators and GPT-4o. These instructions span three major categories and thirteen minor categories, encompassing nearly all important types of web applications. To assess the quality of the generated websites, we use GPT-4o to generate test cases targeting each functionality described in the instructions, and then manually filter, adjust, and organize them to ensure accuracy, resulting in 647 test cases. Each test case specifies an operation to be performed on the website and the expected result after the operation. To automate testing and improve reproducibility, we employ a powerful web-navigation agent to execute tests on the generated websites and determine whether the observed responses align with the expected results. We evaluate three high-performance code-agent frameworks, Bolt.diy, OpenHands, and Aider, using multiple proprietary and open-source LLMs as engines. The best-performing combination, Bolt.diy powered by DeepSeek-R1, achieves only 27.8\% accuracy on the test cases, highlighting the challenging nature of our benchmark. Additionally, we construct WebGen-Instruct, a training set consisting of 6,667 website-generation instructions. Training Qwen2.5-Coder-32B-Instruct on Bolt.diy trajectories generated from a subset of this training set achieves an accuracy of 38.2\%, surpassing the performance of the best proprietary model.

We introduce a novel framework named ClarifyGPT, which aims to enhance code generation by empowering LLMs with the ability to identify ambiguous requirements and ask targeted clarifying questions. In particular, ClarifyGPT first detects whether a given requirement is ambiguous by performing a code consistency check. If it is ambiguous, ClarifyGPT prompts an LLM to generate targeted clarifying questions. After receiving question responses, ClarifyGPT refines the ambiguous requirement and inputs it into the same LLM to generate a final code solution. To evaluate our ClarifyGPT, we first conduct a human evaluation involving ten participants who use ClarifyGPT for code generation on two publicly available benchmarks: MBPP-sanitized and MBPP-ET. The results show that ClarifyGPT elevates the performance (Pass@1) of GPT-4 from 70.96% to 80.80% on MBPP-sanitized. Furthermore, to perform large-scale automated evaluations of ClarifyGPT across different LLMs and benchmarks without requiring user participation, we introduce a high-fidelity simulation method to simulate user responses. The automated evaluation results also demonstrate that ClarifyGPT can significantly enhance code generation performance compared to the baselines. In particular, ClarifyGPT improves the average performance of GPT-4 and ChatGPT across four benchmarks from 68.02% to 75.75% and from 58.55% to 67.22%, respectively. We believe that ClarifyGPT can effectively facilitate the practical application of LLMs in real-world development environments.

Recent advances in image generation, often driven by proprietary systems like GPT-4o Image Gen, regularly introduce new capabilities that reshape how users interact with these models. Existing benchmarks often lag behind and fail to capture these emerging use cases, leaving a gap between community perceptions of progress and formal evaluation. To address this, we present ECHO, a framework for constructing benchmarks directly from real-world evidence of model use: social media posts that showcase novel prompts and qualitative user judgments. Applying this framework to GPT-4o Image Gen, we construct a dataset of over 31,000 prompts curated from such posts. Our analysis shows that ECHO (1) discovers creative and complex tasks absent from existing benchmarks, such as re-rendering product labels across languages or generating receipts with specified totals, (2) more clearly distinguishes state-of-the-art models from alternatives, and (3) surfaces community feedback that we use to inform the design of metrics for model quality (e.g., measuring observed shifts in color, identity, and structure). Our website is at https://echo-bench.github.io.

In this work, we introduce ChatQA, a family of conversational question answering (QA) models, that obtain GPT-4 level accuracies. Specifically, we propose a two-stage instruction tuning method that can significantly improve the zero-shot conversational QA results from large language models (LLMs). To handle retrieval in conversational QA, we fine-tune a dense retriever on a multi-turn QA dataset, which provides comparable results to using the state-of-the-art query rewriting model while largely reducing deployment cost. Notably, our ChatQA-70B can outperform GPT-4 in terms of average score on 10 conversational QA datasets (54.14 vs. 53.90), without relying on any synthetic data from OpenAI GPT models.

Code generation models have increasingly become integral to aiding software development, offering assistance in tasks such as code completion, debugging, and code translation. Although current research has thoroughly examined the correctness of code produced by code generation models, a vital aspect, i.e., the efficiency of the generated code, has often been neglected. This paper presents EffiBench, a benchmark with 1,000 efficiency-critical coding problems for assessing the efficiency of code generated by code generation models. EffiBench contains a diverse set of LeetCode coding problems. Each problem is paired with an executable human-written canonical solution. With EffiBench, we empirically examine the capability of 21 Large Language Models (13 open-sourced and 8 closed-sourced) in generating efficient code. The results demonstrate that GPT-4-turbo generates the most efficient code, significantly outperforming Palm-2-chat-bison, Claude-instant-1, Gemini-pro, GPT-4, and GPT-3.5. Nevertheless, its code efficiency is still worse than the efficiency of human-written canonical solutions. In particular, the average and worst execution time of GPT-4-turbo generated code is 1.69 and 45.49 times that of the canonical solutions.

Large Language Models (LLMs) have demonstrated remarkable success in various natural language processing and software engineering tasks, such as code generation. The LLMs are mainly utilized in the prompt-based zero/few-shot paradigm to guide the model in accomplishing the task. GPT-based models are one of the popular ones studied for tasks such as code comment generation or test generation. These tasks are `generative' tasks. However, there is limited research on the usage of LLMs for `non-generative' tasks such as classification using the prompt-based paradigm. In this preliminary exploratory study, we investigated the applicability of LLMs for Code Clone Detection (CCD), a non-generative task. By building a mono-lingual and cross-lingual CCD dataset derived from CodeNet, we first investigated two different prompts using ChatGPT to detect Type-4 code clones in Java-Java and Java-Ruby pairs in a zero-shot setting. We then conducted an analysis to understand the strengths and weaknesses of ChatGPT in CCD. ChatGPT surpasses the baselines in cross-language CCD attaining an F1-score of 0.877 and achieves comparable performance to fully fine-tuned models for mono-lingual CCD, with an F1-score of 0.878. Also, the prompt and the difficulty level of the problems has an impact on the performance of ChatGPT. Finally we provide insights and future directions based on our initial analysis

Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in capabilities, capturing the interest of practitioners and the public alike. Yet, while the literature on the trustworthiness of GPT models remains limited, practitioners have proposed employing capable GPT models for sensitive applications to healthcare and finance - where mistakes can be costly. To this end, this work proposes a comprehensive trustworthiness evaluation for large language models with a focus on GPT-4 and GPT-3.5, considering diverse perspectives - including toxicity, stereotype bias, adversarial robustness, out-of-distribution robustness, robustness on adversarial demonstrations, privacy, machine ethics, and fairness. Based on our evaluations, we discover previously unpublished vulnerabilities to trustworthiness threats. For instance, we find that GPT models can be easily misled to generate toxic and biased outputs and leak private information in both training data and conversation history. We also find that although GPT-4 is usually more trustworthy than GPT-3.5 on standard benchmarks, GPT-4 is more vulnerable given jailbreaking system or user prompts, potentially due to the reason that GPT-4 follows the (misleading) instructions more precisely. Our work illustrates a comprehensive trustworthiness evaluation of GPT models and sheds light on the trustworthiness gaps. Our benchmark is publicly available at https://decodingtrust.github.io/.

We perform a missing, reproducible evaluation of all publicly available GPT-4 family models concerning the Document Understanding field, where it is frequently required to comprehend text spacial arrangement and visual clues in addition to textual semantics. Benchmark results indicate that though it is hard to achieve satisfactory results with text-only models, GPT-4 Vision Turbo performs well when one provides both text recognized by an external OCR engine and document images on the input. Evaluation is followed by analyses that suggest possible contamination of textual GPT-4 models and indicate the significant performance drop for lengthy documents.

Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) with relevant and up-to-date knowledge, improving their ability to answer knowledge-intensive questions. It has been shown to enhance both generation quality and trustworthiness. While numerous works have focused on improving retrieval, generation, and evaluation, the role of reward models in reinforcement learning for optimizing RAG and establishing automated benchmarking pipelines remains underexplored. In this paper, we introduce RAG-Reward, a dataset designed to enable hallucination-free, comprehensive, reliable, and efficient RAG. We define four key metrics for assessing generation quality and develop an automated annotation pipeline that leverages multiple LLMs to generate outputs across diverse RAG scenarios. GPT-4o is used to evaluate and construct preference data. Using RAG-Reward, we train reward models and apply reinforcement learning with human feedback (RLHF) to improve LLMs' effectiveness in RAG. Experimental results show that our reward model achieves state-of-the-art performance on a held-out test set, demonstrating both the effectiveness of our approach and the quality of our dataset. Furthermore, the improved generation quality of the trained policy model highlights the feasibility of using RLHF to enhance RAG pipelines.

There is great interest in fine-tuning frontier large language models (LLMs) to inject new information and update existing knowledge. While commercial LLM fine-tuning APIs from providers such as OpenAI and Google promise flexible adaptation for various applications, the efficacy of fine-tuning remains unclear. In this study, we introduce FineTuneBench, an evaluation framework and dataset for understanding how well commercial fine-tuning APIs can successfully learn new and updated knowledge. We analyze five frontier LLMs with commercially available fine-tuning APIs, including GPT-4o and Gemini 1.5 Pro, on their effectiveness in two settings: (1) ingesting novel information, such as recent news events and new people profiles, and (2) updating existing knowledge, such as updated medical guidelines and code frameworks. Our results reveal substantial shortcomings in all the models' abilities to effectively learn new information through fine-tuning, with an average generalization accuracy of 37% across all models. When updating existing knowledge, such as incorporating medical guideline updates, commercial fine-tuning APIs show even more limited capability (average generalization accuracy of 19%). Overall, fine-tuning GPT-4o mini is the most effective for infusing new knowledge and updating knowledge, followed by GPT-3.5 Turbo and GPT-4o. The fine-tuning APIs for Gemini 1.5 Flesh and Gemini 1.5 Pro are unable to learn new knowledge or update existing knowledge. These findings underscore a major shortcoming in using current commercial fine-tuning services to achieve reliable knowledge infusion in common scenarios. We open source the FineTuneBench dataset at https://github.com/kevinwu23/StanfordFineTuneBench.

The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation. This issue becomes particularly pronounced when rapidly developing such resources for a non-English language like Japanese. Instead of following the popular practice of directly translating existing English resources into Japanese (e.g., Japanese-Alpaca), we propose an efficient self-instruct method based on GPT-4. We first translate a small amount of English instructions into Japanese and post-edit them to obtain native-level quality. GPT-4 then utilizes them as demonstrations to automatically generate Japanese instruction data. We also construct an evaluation benchmark containing 80 questions across 8 categories, using GPT-4 to automatically assess the response quality of LLMs without human references. The empirical results suggest that the models fine-tuned on our GPT-4 self-instruct data significantly outperformed the Japanese-Alpaca across all three base pre-trained models. Our GPT-4 self-instruct data allowed the LLaMA 13B model to defeat GPT-3.5 (Davinci-003) with a 54.37\% win-rate. The human evaluation exhibits the consistency between GPT-4's assessments and human preference. Our high-quality instruction data and evaluation benchmark have been released here.

The recently released GPT-4 Code Interpreter has demonstrated remarkable proficiency in solving challenging math problems, primarily attributed to its ability to seamlessly reason with natural language, generate code, execute code, and continue reasoning based on the execution output. In this paper, we present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations and, consequently, enhancing their mathematical reasoning abilities. We propose a method of generating novel and high-quality datasets with math problems and their code-based solutions, referred to as MathCodeInstruct. Each solution interleaves natural language, code, and execution results. We also introduce a customized supervised fine-tuning and inference approach. This approach yields the MathCoder models, a family of models capable of generating code-based solutions for solving challenging math problems. Impressively, the MathCoder models achieve state-of-the-art scores among open-source LLMs on the MATH (45.2%) and GSM8K (83.9%) datasets, substantially outperforming other open-source alternatives. Notably, the MathCoder model not only surpasses ChatGPT-3.5 and PaLM-2 on GSM8K and MATH but also outperforms GPT-4 on the competition-level MATH dataset. The dataset and models will be released at https://github.com/mathllm/MathCoder.

Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style programming hints to help students resolve errors in their buggy programs. Recent works have benchmarked state-of-the-art models for various feedback generation scenarios; however, their overall quality is still inferior to human tutors and not yet ready for real-world deployment. In this paper, we seek to push the limits of generative AI models toward providing high-quality programming hints and develop a novel technique, GPT4Hints-GPT3.5Val. As a first step, our technique leverages GPT-4 as a ``tutor'' model to generate hints -- it boosts the generative quality by using symbolic information of failing test cases and fixes in prompts. As a next step, our technique leverages GPT-3.5, a weaker model, as a ``student'' model to further validate the hint quality -- it performs an automatic quality validation by simulating the potential utility of providing this feedback. We show the efficacy of our technique via extensive evaluation using three real-world datasets of Python programs covering a variety of concepts ranging from basic algorithms to regular expressions and data analysis using pandas library.

Current text-to-image (T2I) generation models achieve promising results, but they fail on the scenarios where the knowledge implied in the text prompt is uncertain. For example, a T2I model released in February would struggle to generate a suitable poster for a movie premiering in April, because the character designs and styles are uncertain to the model. To solve this problem, we propose an Internet-Augmented text-to-image generation (IA-T2I) framework to compel T2I models clear about such uncertain knowledge by providing them with reference images. Specifically, an active retrieval module is designed to determine whether a reference image is needed based on the given text prompt; a hierarchical image selection module is introduced to find the most suitable image returned by an image search engine to enhance the T2I model; a self-reflection mechanism is presented to continuously evaluate and refine the generated image to ensure faithful alignment with the text prompt. To evaluate the proposed framework's performance, we collect a dataset named Img-Ref-T2I, where text prompts include three types of uncertain knowledge: (1) known but rare. (2) unknown. (3) ambiguous. Moreover, we carefully craft a complex prompt to guide GPT-4o in making preference evaluation, which has been shown to have an evaluation accuracy similar to that of human preference evaluation. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4o by about 30% in human evaluation.

Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are needed. In this paper, we present the first attempt to use GPT-4 to generate instruction-following data for LLM finetuning. Our early experiments on instruction-tuned LLaMA models show that the 52K English and Chinese instruction-following data generated by GPT-4 leads to superior zero-shot performance on new tasks to the instruction-following data generated by previous state-of-the-art models. We also collect feedback and comparison data from GPT-4 to enable a comprehensive evaluation and reward model training. We make our data generated using GPT-4 as well as our codebase publicly available.

Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models. Nevertheless, assessing the quality of the generation is an even more arduous task than the generation itself, and this issue has not been given adequate consideration recently. This paper proposes a novel evaluation framework, GPTScore, which utilizes the emergent abilities (e.g., zero-shot instruction) of generative pre-trained models to score generated texts. There are 19 pre-trained models explored in this paper, ranging in size from 80M (e.g., FLAN-T5-small) to 175B (e.g., GPT3). Experimental results on four text generation tasks, 22 evaluation aspects, and corresponding 37 datasets demonstrate that this approach can effectively allow us to achieve what one desires to evaluate for texts simply by natural language instructions. This nature helps us overcome several long-standing challenges in text evaluation--how to achieve customized, multi-faceted evaluation without the need for annotated samples. We make our code publicly available at https://github.com/jinlanfu/GPTScore.

Multi-hop QA (MHQA) involves step-by-step reasoning to answer complex questions and find multiple relevant supporting facts. However, Existing large language models'(LLMs) reasoning ability in multi-hop question answering remains exploration, which is inadequate in answering multi-hop questions. Moreover, it is unclear whether LLMs follow a desired reasoning chain to reach the right final answer. In this paper, we propose a generative question decomposition method (GenDec) from the perspective of explainable QA by generating independent and complete sub-questions based on incorporating additional extracted evidence for enhancing LLMs' reasoning ability in RAG. To demonstrate the impact, generalization, and robustness of Gendec, we conduct two experiments, the first is combining GenDec with small QA systems on paragraph retrieval and QA tasks. We secondly examine the reasoning capabilities of various state-of-the-art LLMs including GPT-4 and GPT-3.5 combined with GenDec. We experiment on the HotpotQA, 2WikihopMultiHopQA, MuSiQue, and PokeMQA datasets.

Engineering Design is undergoing a transformative shift with the advent of AI, marking a new era in how we approach product, system, and service planning. Large language models have demonstrated impressive capabilities in enabling this shift. Yet, with text as their only input modality, they cannot leverage the large body of visual artifacts that engineers have used for centuries and are accustomed to. This gap is addressed with the release of multimodal vision language models, such as GPT-4V, enabling AI to impact many more types of tasks. In light of these advancements, this paper presents a comprehensive evaluation of GPT-4V, a vision language model, across a wide spectrum of engineering design tasks, categorized into four main areas: Conceptual Design, System-Level and Detailed Design, Manufacturing and Inspection, and Engineering Education Tasks. Our study assesses GPT-4V's capabilities in design tasks such as sketch similarity analysis, concept selection using Pugh Charts, material selection, engineering drawing analysis, CAD generation, topology optimization, design for additive and subtractive manufacturing, spatial reasoning challenges, and textbook problems. Through this structured evaluation, we not only explore GPT-4V's proficiency in handling complex design and manufacturing challenges but also identify its limitations in complex engineering design applications. Our research establishes a foundation for future assessments of vision language models, emphasizing their immense potential for innovating and enhancing the engineering design and manufacturing landscape. It also contributes a set of benchmark testing datasets, with more than 1000 queries, for ongoing advancements and applications in this field.

Context: Test-driven development (TDD) is a widely employed software development practice that involves developing test cases based on requirements prior to writing the code. Although various methods for automated test case generation have been proposed, they are not specifically tailored for TDD, where requirements instead of code serve as input. Objective: In this paper, we introduce a text-to-testcase generation approach based on a large language model (GPT-3.5) that is fine-tuned on our curated dataset with an effective prompt design. Method: Our approach involves enhancing the capabilities of basic GPT-3.5 for text-to-testcase generation task that is fine-tuned on our curated dataset with an effective prompting design. We evaluated the effectiveness of our approach using a span of five large-scale open-source software projects. Results: Our approach generated 7k test cases for open source projects, achieving 78.5% syntactic correctness, 67.09% requirement alignment, and 61.7% code coverage, which substantially outperforms all other LLMs (basic GPT-3.5, Bloom, and CodeT5). In addition, our ablation study demonstrates the substantial performance improvement of the fine-tuning and prompting components of the GPT-3.5 model. Conclusions: These findings lead us to conclude that fine-tuning and prompting should be considered in the future when building a language model for the text-to-testcase generation task

The impressive performance of Large Language Models (LLMs) has consistently surpassed numerous human-designed benchmarks, presenting new challenges in assessing the shortcomings of LLMs. Designing tasks and finding LLMs' limitations are becoming increasingly important. In this paper, we investigate the question of whether an LLM can discover its own limitations from the errors it makes. To this end, we propose a Self-Challenge evaluation framework with human-in-the-loop. Starting from seed instances that GPT-4 fails to answer, we prompt GPT-4 to summarize error patterns that can be used to generate new instances and incorporate human feedback on them to refine these patterns for generating more challenging data, iteratively. We end up with 8 diverse patterns, such as text manipulation and questions with assumptions. We then build a benchmark, SC-G4, consisting of 1,835 instances generated by GPT-4 using these patterns, with human-annotated gold responses. The SC-G4 serves as a challenging benchmark that allows for a detailed assessment of LLMs' abilities. Our results show that only 44.96\% of instances in SC-G4 can be answered correctly by GPT-4. Interestingly, our pilot study indicates that these error patterns also challenge other LLMs, such as Claude-3 and Llama-3, and cannot be fully resolved through fine-tuning. Our work takes the first step to demonstrate that LLMs can autonomously identify their inherent flaws and provide insights for future dynamic and automatic evaluation.

As large language models (LLMs) have demonstrated their powerful capabilities in plenty of domains and tasks, including context understanding, code generation, language generation, data storytelling, etc., many data analysts may raise concerns if their jobs will be replaced by AI. This controversial topic has drawn a lot of attention in public. However, we are still at a stage of divergent opinions without any definitive conclusion. Motivated by this, we raise the research question of "is GPT-4 a good data analyst?" in this work and aim to answer it by conducting head-to-head comparative studies. In detail, we regard GPT-4 as a data analyst to perform end-to-end data analysis with databases from a wide range of domains. We propose a framework to tackle the problems by carefully designing the prompts for GPT-4 to conduct experiments. We also design several task-specific evaluation metrics to systematically compare the performance between several professional human data analysts and GPT-4. Experimental results show that GPT-4 can achieve comparable performance to humans. We also provide in-depth discussions about our results to shed light on further studies before we reach the conclusion that GPT-4 can replace data analysts.

Large Language Models (LLMs) have demonstrated great potential in various language processing tasks, and recent studies have explored their application in compiler optimizations. However, all these studies focus on the conventional open-source LLMs, such as Llama2, which lack enhanced reasoning mechanisms. In this study, we investigate the errors produced by the fine-tuned 7B-parameter Llama2 model as it attempts to learn and apply a simple peephole optimization for the AArch64 assembly code. We provide an analysis of the errors produced by the LLM and compare it with state-of-the-art OpenAI models which implement advanced reasoning logic, including GPT-4o and GPT-o1 (preview). We demonstrate that OpenAI GPT-o1, despite not being fine-tuned, outperforms the fine-tuned Llama2 and GPT-4o. Our findings indicate that this advantage is largely due to the chain-of-thought reasoning implemented in GPT-o1. We hope our work will inspire further research on using LLMs with enhanced reasoning mechanisms and chain-of-thought for code generation and optimization.

Large Language Models (LLMs) have sparked significant interest in their generative capabilities, leading to the development of various commercial applications. The high cost of using the models drives application builders to maximize the value of generation under a limited inference budget. This paper presents a study of optimizing inference hyperparameters such as the number of responses, temperature and max tokens, which significantly affects the utility/cost of text generation. We design a framework named EcoOptiGen which leverages economical hyperparameter optimization and cost-based pruning. Experiments with the GPT-3.5/GPT-4 models on a variety of tasks verify its effectiveness. EcoOptiGen is implemented in the `autogen' package of the FLAML library: https://aka.ms/autogen.

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to automatically assess the impact of various prompt engineering strategies on code security. Our benchmark leverages two peer-reviewed prompt datasets and employs static scanners to evaluate code security at scale. We tested multiple prompt engineering techniques on GPT-3.5-turbo, GPT-4o, and GPT-4o-mini. Our results show that for GPT-4o and GPT-4o-mini, a security-focused prompt prefix can reduce the occurrence of security vulnerabilities by up to 56%. Additionally, all tested models demonstrated the ability to detect and repair between 41.9% and 68.7% of vulnerabilities in previously generated code when using iterative prompting techniques. Finally, we introduce a "prompt agent" that demonstrates how the most effective techniques can be applied in real-world development workflows.

Large language models (LLMs) can respond to human language queries and have shown powerful potential applications in network operations (NetOps). Thanks to the large amount of commonsense knowledge inherent, LLMs achieve much better inference accuracy than traditional models and emerge with strong abilities in generalization, reasoning, and code generation. These abilities may have a crucial boost to automated and intelligent NetOps. However, it remains under-explored how well LLMs perform in various NetOps tasks. In this work, we make a systematic assessment of the capabilities, strengths, and limitations of selected LLMs in the field of NetOps. The evaluation is conducted on a collection of 5,732 questions about NetOps, encompassing 26 publicly available general-domain LLMs, including ChatGPT, LLaMA, Falcon, etc. We also finetune some of these LLMs with our collected NetOps corpus and evaluate the resulting models. The evaluation method follows the widely adopted benchmarks for general-domain LLMs, combined with Chain-of-Thought Prompts and Retrieval-Augmented Generation. The results show that only GPT-4 achieves high accuracy equivalent to passing the NetOps certification exam for humans, while all the other LLMs have much lower accuracy. However, some open models like LLaMA 2 still demonstrate significant potential. Furthermore, we evaluate the impact of factors such as model parameters, prompt engineering, instruction fine-tuning etc. This work shall be treated as the initial effort to systematic evaluation of LLMs in NetOps, and a more rigorous study is required for production use. The evaluation code and dataset will be released to benefit future research.

Generalist foundation models such as GPT-4 have displayed surprising capabilities in a wide variety of domains and tasks. Yet, there is a prevalent assumption that they cannot match specialist capabilities of fine-tuned models. For example, most explorations to date on medical competency benchmarks have leveraged domain-specific training, as exemplified by efforts on BioGPT and Med-PaLM. We build on a prior study of GPT-4's capabilities on medical challenge benchmarks in the absence of special training. Rather than using simple prompting to highlight the model's out-of-the-box capabilities, we perform a systematic exploration of prompt engineering. We find that prompting innovation can unlock deeper specialist capabilities and show that GPT-4 easily tops prior leading results for medical benchmarks. The prompting methods we explore are general purpose, and make no specific use of domain expertise, removing the need for expert-curated content. Our experimental design carefully controls for overfitting during the prompt engineering process. We introduce Medprompt, based on a composition of several prompting strategies. With Medprompt, GPT-4 achieves state-of-the-art results on all nine of the benchmark datasets in the MultiMedQA suite. The method outperforms leading specialist models such as Med-PaLM 2 by a significant margin with an order of magnitude fewer calls to the model. Steering GPT-4 with Medprompt achieves a 27% reduction in error rate on the MedQA dataset over the best methods to date achieved with specialist models and surpasses a score of 90% for the first time. Beyond medical problems, we show the power of Medprompt to generalize to other domains and provide evidence for the broad applicability of the approach via studies of the strategy on exams in electrical engineering, machine learning, philosophy, accounting, law, nursing, and clinical psychology.

Large Language Models (LLMs) have shown remarkable aptitude in code generation but still struggle on challenging programming tasks. Self-repair -- in which the model debugs and fixes mistakes in its own code -- has recently become a popular way to boost performance in these settings. However, only very limited studies on how and when self-repair works effectively exist in the literature, and one might wonder to what extent a model is really capable of providing accurate feedback on why the code is wrong when that code was generated by the same model. In this paper, we analyze GPT-3.5 and GPT-4's ability to perform self-repair on APPS, a challenging dataset consisting of diverse coding challenges. To do so, we first establish a new evaluation strategy dubbed pass@t that measures the pass rate of the tasks against the total number of tokens sampled from the model, enabling a fair comparison to purely sampling-based approaches. With this evaluation strategy, we find that the effectiveness of self-repair is only seen in GPT-4. We also observe that self-repair is bottlenecked by the feedback stage; using GPT-4 to give feedback on the programs generated by GPT-3.5 and using expert human programmers to give feedback on the programs generated by GPT-4, we unlock significant performance gains.

Large Language Models (LLMs) for code generation evolve rapidly through fine-tuning, merging, or new model releases. However, such updates can introduce regressions, not only in correctness but also in code quality and performance. To address this, we present ReCatcher, a regression testing framework for Python code generation. ReCatcher systematically compares two LLMs, typically a current model and a candidate update, across three dimensions: logical correctness, static code quality, and execution performance. We apply ReCatcher to assess regressions across three update scenarios, fine-tuning, merging, and model release, using CodeLlama, DeepSeek-Coder, and GPT-4o. Our evaluation shows that fine-tuning with cross-language datasets increases syntax errors by up to 12%. Merging with general-purpose models like Llama2 leads to regressions in correctness by up to 18%. GPT-4o introduces regressions of up to 50% in handling missing imports compared to GPT-3.5-turbo, while GPT-4o-mini suffers up to 80% performance degradation in execution time versus GPT-4o. Overall, logical correctness, performance, and error handling (e.g., syntax errors and missing imports) are the most regression-prone areas. Comparing ReCatcher with baseline solutions, it presents better and consistent accuracy across logical and performance aspects. ReCatcher highlights the importance of systematic regression evaluation before adopting new models, while assisting researchers and practitioners in making more informed update decisions.

Software testing is a crucial aspect of software development, and the creation of high-quality tests that adhere to best practices is essential for effective maintenance. Recently, Large Language Models (LLMs) have gained popularity for code generation, including the automated creation of test cases. However, these LLMs are often trained on vast amounts of publicly available code, which may include test cases that do not adhere to best practices and may even contain test smells (anti-patterns). To address this issue, we propose a novel technique called Reinforcement Learning from Static Quality Metrics (RLSQM). To begin, we analyze the anti-patterns generated by the LLM and show that LLMs can generate undesirable test smells. Thus, we train specific reward models for each static quality metric, then utilize Proximal Policy Optimization (PPO) to train models for optimizing a single quality metric at a time. Furthermore, we amalgamate these rewards into a unified reward model aimed at capturing different best practices and quality aspects of tests. By comparing RL-trained models with those trained using supervised learning, we provide insights into how reliably utilize RL to improve test generation quality and into the effects of various training strategies. Our experimental results demonstrate that the RL-optimized model consistently generated high-quality test cases compared to the base LLM, improving the model by up to 21%, and successfully generates nearly 100% syntactically correct code. RLSQM also outperformed GPT-4 on four out of seven metrics. This represents a significant step towards enhancing the overall efficiency and reliability of software testing through Reinforcement Learning and static quality metrics. Our data are available at this link: https://figshare.com/s/ded476c8d4c221222849.

Unit testing is essential in detecting bugs in functionally-discrete program units. Manually writing high-quality unit tests is time-consuming and laborious. Although traditional techniques can generate tests with reasonable coverage, they exhibit low readability and cannot be directly adopted by developers. Recent work has shown the large potential of large language models (LLMs) in unit test generation, which can generate more human-like and meaningful test code. ChatGPT, the latest LLM incorporating instruction tuning and reinforcement learning, has performed well in various domains. However, It remains unclear how effective ChatGPT is in unit test generation. In this work, we perform the first empirical study to evaluate ChatGPT's capability of unit test generation. Specifically, we conduct a quantitative analysis and a user study to systematically investigate the quality of its generated tests regarding the correctness, sufficiency, readability, and usability. The tests generated by ChatGPT still suffer from correctness issues, including diverse compilation errors and execution failures. Still, the passing tests generated by ChatGPT resemble manually-written tests by achieving comparable coverage, readability, and even sometimes developers' preference. Our findings indicate that generating unit tests with ChatGPT could be very promising if the correctness of its generated tests could be further improved. Inspired by our findings above, we propose ChatTESTER, a novel ChatGPT-based unit test generation approach, which leverages ChatGPT itself to improve the quality of its generated tests. ChatTESTER incorporates an initial test generator and an iterative test refiner. Our evaluation demonstrates the effectiveness of ChatTESTER by generating 34.3% more compilable tests and 18.7% more tests with correct assertions than the default ChatGPT.

Unit testing is a core practice in programming, enabling systematic evaluation of programs produced by human developers or large language models (LLMs). Given the challenges in writing comprehensive unit tests, LLMs have been employed to automate test generation, yet methods for training LLMs to produce high-quality tests remain underexplored. In this work, we propose UTRL, a novel reinforcement learning framework that trains an LLM to generate high-quality unit tests given a programming instruction. Our key idea is to iteratively train two LLMs, the unit test generator and the code generator, in an adversarial manner via reinforcement learning. The unit test generator is trained to maximize a discrimination reward, which reflects its ability to produce tests that expose faults in the code generator's solutions, and the code generator is trained to maximize a code reward, which reflects its ability to produce solutions that pass the unit tests generated by the test generator. In our experiments, we demonstrate that unit tests generated by Qwen3-4B trained via UTRL show higher quality compared to unit tests generated by the same model trained via supervised fine-tuning on human-written ground-truth unit tests, yielding code evaluations that more closely align with those induced by the ground-truth tests. Moreover, Qwen3-4B trained with UTRL outperforms frontier models such as GPT-4.1 in generating high-quality unit tests, highlighting the effectiveness of UTRL in training LLMs for this task.

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code generation, even minor errors can easily break the entire solution. Leveraging multiple sampled solutions can significantly improve the overall output quality. One effective way to enhance code generation is by pairing a code generation model with a reranker model, which selects the best solution from the generated samples. We propose a novel iterative self-training approach for self-training reranker models using Proximal Policy Optimization (PPO), aimed at improving both reranking accuracy and the overall code generation process. Unlike traditional PPO approaches, where the focus is on optimizing a generative model with a reward model, our approach emphasizes the development of a robust reward/reranking model. This model improves the quality of generated code through reranking and addresses problems and errors that the reward model might overlook during PPO alignment with the reranker. Our method iteratively refines the training dataset by re-evaluating outputs, identifying high-scoring negative examples, and incorporating them into the training loop, that boosting model performance. Our evaluation on the MultiPL-E dataset demonstrates that our 13.4B parameter model outperforms a 33B model in code generation quality while being three times faster. Moreover, it achieves performance comparable to GPT-4 and surpasses it in one programming language.

Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance, particularly in intricate web environments and long-horizon planning tasks. To address these limitations, we introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test-time algorithm designed to enhance the ability of AI agents, e.g., powered by GPT-4o, to explore decision space on the fly. R-MCTS extends traditional MCTS by 1) incorporating contrastive reflection, allowing agents to learn from past interactions and dynamically improve their search efficiency; and 2) using multi-agent debate to provide reliable state evaluation. Moreover, we improve the agent's performance by fine-tuning GPT-4o through self-learning, using R-MCTS generated tree traversals without any human-provided labels. On the challenging VisualWebArena benchmark, our GPT-4o-based R-MCTS agent achieves a 6% to 30% relative improvement across various tasks compared to the previous state-of-the-art. Additionally, we show that the knowledge gained from test-time search can be effectively transferred back to GPT-4o via fine-tuning. The fine-tuned GPT-4o matches 97% of R-MCTS's performance while reducing compute usage by a factor of four at test time. Furthermore, qualitative results reveal that the fine-tuned GPT-4o model demonstrates the ability to explore the environment, evaluate a state, and backtrack to viable ones when it detects that the current state cannot lead to success. Moreover, our work demonstrates the compute scaling properties in both training - data collection with R-MCTS - and testing time. These results suggest a promising research direction to enhance VLMs' reasoning and planning capabilities for agentic applications via test-time search and self-learning.

We introduce REALTIME QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis (weekly in this version). REALTIME QA inquires about the current world, and QA systems need to answer questions about novel events or information. It therefore challenges static, conventional assumptions in open-domain QA datasets and pursues instantaneous applications. We build strong baseline models upon large pretrained language models, including GPT-3 and T5. Our benchmark is an ongoing effort, and this paper presents real-time evaluation results over the past year. Our experimental results show that GPT-3 can often properly update its generation results, based on newly-retrieved documents, highlighting the importance of up-to-date information retrieval. Nonetheless, we find that GPT-3 tends to return outdated answers when retrieved documents do not provide sufficient information to find an answer. This suggests an important avenue for future research: can an open-domain QA system identify such unanswerable cases and communicate with the user or even the retrieval module to modify the retrieval results? We hope that REALTIME QA will spur progress in instantaneous applications of question answering and beyond.

Generative AI and large language models hold great promise in enhancing computing education by powering next-generation educational technologies for introductory programming. Recent works have studied these models for different scenarios relevant to programming education; however, these works are limited for several reasons, as they typically consider already outdated models or only specific scenario(s). Consequently, there is a lack of a systematic study that benchmarks state-of-the-art models for a comprehensive set of programming education scenarios. In our work, we systematically evaluate two models, ChatGPT (based on GPT-3.5) and GPT-4, and compare their performance with human tutors for a variety of scenarios. We evaluate using five introductory Python programming problems and real-world buggy programs from an online platform, and assess performance using expert-based annotations. Our results show that GPT-4 drastically outperforms ChatGPT (based on GPT-3.5) and comes close to human tutors' performance for several scenarios. These results also highlight settings where GPT-4 still struggles, providing exciting future directions on developing techniques to improve the performance of these models.

Understanding telecom standards involves sorting through numerous technical documents, such as those produced by the 3rd Generation Partnership Project (3GPP), which is time-consuming and labor-intensive. While large language models (LLMs) can assist with the extensive 3GPP knowledge base, an inclusive dataset is crucial for their effective pre-training and fine-tuning. In this paper, we introduce TSpec-LLM, an open-source comprehensive dataset covering all 3GPP documents from Release 8 to Release 19 (1999--2023). To evaluate its efficacy, we first select a representative sample of 3GPP documents, create corresponding technical questions, and assess the baseline performance of various LLMs. We then incorporate a retrieval-augmented generation (RAG) framework to enhance LLM capabilities by retrieving relevant context from the TSpec-LLM dataset. Our evaluation shows that using a naive-RAG framework on TSpec-LLM improves the accuracy of GPT-3.5, Gemini 1.0 Pro, and GPT-4 from 44\%, 46\%, and 51\% to 71\%, 75\%, and 72\%, respectively.

Existing math datasets evaluate the reasoning abilities of large language models (LLMs) by either using the final answer or the intermediate reasoning steps derived from static examples. However, the former approach fails to surface model's uses of shortcuts and wrong reasoning while the later poses challenges in accommodating alternative solutions. In this work, we seek to use symbolic programs as a means for automated evaluation if a model can consistently produce correct final answers across various inputs to the program. We begin by extracting programs for popular math datasets (GSM8K and MATH) using GPT4-o. For those executable programs verified using the original input-output pairs, they are found to encapsulate the proper reasoning required to solve the original text questions. We then prompt GPT4-o to generate new questions using alternative input-output pairs based the extracted program. We apply the resulting datasets to evaluate a collection of LLMs. In our experiments, we observe significant accuracy drops using our proposed evaluation compared with original static examples, suggesting the fragility of math reasoning in state-of-the-art LLMs.

Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about these abilities and the potential data contamination problem recently. This paper aims to evaluate the reasoning capacities of LLMs, specifically in solving recent competition-level programming problems in Codeforces, which are expert-crafted and unique, requiring deep understanding and robust reasoning skills. We first provide a comprehensive evaluation of GPT-4's peiceived zero-shot performance on this task, considering various aspects such as problems' release time, difficulties, and types of errors encountered. Surprisingly, the peiceived performance of GPT-4 has experienced a cliff like decline in problems after September 2021 consistently across all the difficulties and types of problems, which shows the potential data contamination, as well as the challenges for any existing LLM to solve unseen complex reasoning problems. We further explore various approaches such as fine-tuning, Chain-of-Thought prompting and problem description simplification, unfortunately none of them is able to consistently mitigate the challenges. Through our work, we emphasis the importance of this excellent data source for assessing the genuine reasoning capabilities of LLMs, and foster the development of LLMs with stronger reasoning abilities and better generalization in the future.

Software testing is a crucial phase in the software life cycle, helping identify potential risks and reduce maintenance costs. With the advancement of Large Language Models (LLMs), researchers have proposed an increasing number of LLM-based software testing techniques, particularly in the area of test case generation. Despite the growing interest, limited efforts have been made to thoroughly evaluate the actual capabilities of LLMs in this task. In this paper, we introduce TestBench, a benchmark for class-level LLM-based test case generation. We construct a dataset of 108 Java programs from 9 real-world, large-scale projects on GitHub, each representing a different thematic domain. We then design three distinct types of prompts based on context descriptions, including self-contained context, full context, and simple context. Besides, we propose a fine-grained evaluation framework that considers five aspects of test cases: syntactic correctness, compilation correctness, test correctness, code coverage rate, and defect detection rate. Furthermore, we propose a heuristic algorithm to repair erroneous test cases generated by LLMs. We evaluate CodeLlama-13b, GPT-3.5, and GPT-4 on the TestBench, and our experimental results indicate that larger models demonstrate a greater ability to effectively utilize contextual information, thus generating higher-quality test cases. Smaller models may struggle with the noise introduced by the extensive information contained within the full context. However, when using the simplified version, namely the simple context, which is derived from the full context via abstract syntax tree analysis, the performance of these models improves significantly. Our analysis highlights the current progress and pinpoints future directions to further enhance the effectiveness of models by handling contextual information for test case generation.

In this work, we introduce a novel evaluation paradigm for Large Language Models, one that challenges them to engage in meta-reasoning. This approach addresses critical shortcomings in existing math problem-solving benchmarks, traditionally used to evaluate the cognitive capabilities of agents. Our paradigm shifts the focus from result-oriented assessments, which often overlook the reasoning process, to a more holistic evaluation that effectively differentiates the cognitive capabilities among models. For example, in our benchmark, GPT-4 demonstrates a performance ten times more accurate than GPT3-5. The significance of this new paradigm lies in its ability to reveal potential cognitive deficiencies in LLMs that current benchmarks, such as GSM8K, fail to uncover due to their saturation and lack of effective differentiation among varying reasoning abilities. Our comprehensive analysis includes several state-of-the-art math models from both open-source and closed-source communities, uncovering fundamental deficiencies in their training and evaluation approaches. This paper not only advocates for a paradigm shift in the assessment of LLMs but also contributes to the ongoing discourse on the trajectory towards Artificial General Intelligence (AGI). By promoting the adoption of meta-reasoning evaluation methods similar to ours, we aim to facilitate a more accurate assessment of the true cognitive abilities of LLMs.

In this study, we evaluated the capability of Large Language Models (LLMs), particularly OpenAI's GPT-4, in detecting software vulnerabilities, comparing their performance against traditional static code analyzers like Snyk and Fortify. Our analysis covered numerous repositories, including those from NASA and the Department of Defense. GPT-4 identified approximately four times the vulnerabilities than its counterparts. Furthermore, it provided viable fixes for each vulnerability, demonstrating a low rate of false positives. Our tests encompassed 129 code samples across eight programming languages, revealing the highest vulnerabilities in PHP and JavaScript. GPT-4's code corrections led to a 90% reduction in vulnerabilities, requiring only an 11% increase in code lines. A critical insight was LLMs' ability to self-audit, suggesting fixes for their identified vulnerabilities and underscoring their precision. Future research should explore system-level vulnerabilities and integrate multiple static code analyzers for a holistic perspective on LLMs' potential.

Recently, there has been a growing trend of utilizing Large Language Model (LLM) to evaluate the quality of other LLMs. Many studies have employed proprietary close-source models, especially GPT4, as the evaluator. Alternatively, other works have fine-tuned judge models based on open-source LLMs as the evaluator. In this study, we conduct an empirical study of different judge models on their evaluation capability. Our findings indicate that although the fine-tuned judge models achieve high accuracy on in-domain test sets, even surpassing GPT4, they are inherently task-specific classifiers, and their generalizability and fairness severely underperform GPT4.

LLM agents enhanced by tree search algorithms have yielded notable performances in code generation. However, current search algorithms in this domain suffer from low search quality due to several reasons: 1) Ineffective design of the search space for the high-reasoning demands of code generation tasks, 2) Inadequate integration of code feedback with the search algorithm, and 3) Poor handling of negative feedback during the search, leading to reduced search efficiency and quality. To address these challenges, we propose to search for the reasoning process of the code and use the detailed feedback of code execution to refine erroneous thoughts during the search. In this paper, we introduce RethinkMCTS, which employs the Monte Carlo Tree Search (MCTS) algorithm to conduct thought-level searches before generating code, thereby exploring a wider range of strategies. More importantly, we construct verbal feedback from fine-grained code execution feedback to refine erroneous thoughts during the search. This ensures that the search progresses along the correct reasoning paths, thus improving the overall search quality of the tree by leveraging execution feedback. Through extensive experiments, we demonstrate that RethinkMCTS outperforms previous search-based and feedback-based code generation baselines. On the HumanEval dataset, it improves the pass@1 of GPT-3.5-turbo from 70.12 to 89.02 and GPT-4o-mini from 87.20 to 94.51. It effectively conducts more thorough exploration through thought-level searches and enhances the search quality of the entire tree by incorporating rethink operation.

We present a novel approach to personalized sleep health management using few-shot Chain-of-Thought (CoT) distillation, enabling small-scale language models (> 2B parameters) to rival the performance of large language models (LLMs) in specialized health domains. Our method simultaneously distills problem-solving strategies, long-tail expert knowledge, and personalized recommendation capabilities from larger models into more efficient, compact models. Unlike existing systems, our approach offers three key functionalities: generating personalized sleep health recommendations, supporting user-specific follow-up inquiries, and providing responses to domain-specific knowledge questions. We focus on sleep health due to its measurability via wearable devices and its impact on overall well-being. Our experimental setup, involving GPT-4o for data synthesis, Qwen-max for instruction set creation, and Qwen2.5 1.5B for model distillation, demonstrates significant improvements over baseline small-scale models in penalization, reasoning, and knowledge application. Experiments using 100 simulated sleep reports and 1,000 domain-specific questions shows our model achieves comparable performance to larger models while maintaining efficiency for real-world deployment. This research not only advances AI-driven health management but also provides a novel approach to leveraging LLM capabilities in resource-constrained environments, potentially enhancing the accessibility of personalized healthcare solutions.

The recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90\% accuracy. However, their capabilities to solve more challenging math problems which require domain-specific knowledge (i.e. theorem) have yet to be investigated. In this paper, we introduce TheoremQA, the first theorem-driven question-answering dataset designed to evaluate AI models' capabilities to apply theorems to solve challenging science problems. \dataset is curated by domain experts containing 800 high-quality questions covering 350 theoremse.g. Taylor's theorem, Lagrange's theorem, Huffman coding, Quantum Theorem, Elasticity Theorem, etc from Math, Physics, EE\&CS, and Finance. We evaluate a wide spectrum of 16 large language and code models with different prompting strategies like Chain-of-Thoughts and Program-of-Thoughts. We found that GPT-4's capabilities to solve these problems are unparalleled, achieving an accuracy of 51\% with Program-of-Thoughts Prompting. All the existing open-sourced models are below 15\%, barely surpassing the random-guess baseline. Given the diversity and broad coverage of \dataset, we believe it can be used as a better benchmark to evaluate LLMs' capabilities to solve challenging science problems. The data and code are released in https://github.com/wenhuchen/TheoremQA.

The application of large-language models (LLMs) to digital hardware code generation is an emerging field. Most LLMs are primarily trained on natural language and software code. Hardware code, such as Verilog, represents only a small portion of the training data and few hardware benchmarks exist. To address this gap, the open-source VerilogEval benchmark was released in 2023, providing a consistent evaluation framework for LLMs on code completion tasks. It was tested on state-of-the-art models at the time including GPT-4. However, VerilogEval and other Verilog generation benchmarks lack failure analysis and, in present form, are not conducive to exploring prompting techniques. Also, since VerilogEval's release, both commercial and open-source models have seen continued development. In this work, we evaluate new commercial and open-source models of varying sizes against an improved VerilogEval benchmark suite. We enhance VerilogEval's infrastructure and dataset by automatically classifying failures, introduce new prompts for supporting in-context learning (ICL) examples, and extend the supported tasks to specification-to-RTL translation. We find a measurable improvement in commercial state-of-the-art models, with GPT-4 Turbo achieving a 59% pass rate on spec-to-RTL tasks. We also study the performance of open-source and domain-specific models that have emerged, and demonstrate that models can benefit substantially from ICL. We find that recently-released Llama 3.1 405B achieves a pass rate of 58%, effectively matching that of GPT-4 Turbo, and that the much smaller domain-specific RTL-Coder 6.7B models achieve an impressive 37% pass rate. However, prompt engineering is key to achieving good pass rates, and varies widely with model and task. A benchmark infrastructure that allows for prompt engineering and failure analysis is key to continued model development and deployment.

Large Language Models (LLMs) have demonstrated impressive performance in software engineering tasks. However, improving their accuracy in generating correct and reliable code remains challenging. Numerous prompt engineering techniques (PETs) have been developed to address this, but no single approach is universally optimal. Selecting the right PET for each query is difficult for two primary reasons: (1) interactive prompting techniques may not consistently deliver the expected benefits, especially for simpler queries, and (2) current automated prompt engineering methods lack adaptability and fail to fully utilize multi-stage responses. To overcome these challenges, we propose PET-Select, a PET-agnostic selection model that uses code complexity as a proxy to classify queries and select the most appropriate PET. By incorporating contrastive learning, PET-Select effectively distinguishes between simple and complex problems, allowing it to choose PETs that are best suited for each query's complexity level. Our evaluations on the MBPP and HumanEval benchmarks using GPT-3.5 Turbo and GPT-4o show up to a 1.9% improvement in pass@1 accuracy, along with a 74.8% reduction in token usage. Additionally, we provide both quantitative and qualitative results to demonstrate how PET-Select effectively selects the most appropriate techniques for each code generation query, further showcasing its efficiency in optimizing PET selection.

As large language models (LLMs) advance, the ultimate vision for their role in science is emerging: we could build an AI collaborator to effectively assist human beings throughout the entire scientific research process. We refer to this envisioned system as ResearchGPT. Given that scientific research progresses through multiple interdependent phases, achieving this vision requires rigorous benchmarks that evaluate the end-to-end workflow rather than isolated sub-tasks. To this end, we contribute CS-54k, a high-quality corpus of scientific Q&A pairs in computer science, built from 14k CC-licensed papers. It is constructed through a scalable, paper-grounded pipeline that combines retrieval-augmented generation (RAG) with multi-stage quality control to ensure factual grounding. From this unified corpus, we derive two complementary subsets: CS-4k, a carefully curated benchmark for evaluating AI's ability to assist scientific research, and CS-50k, a large-scale training dataset. Extensive experiments demonstrate that CS-4k stratifies state-of-the-art LLMs into distinct capability tiers. Open models trained on CS-50k with supervised training and reinforcement learning demonstrate substantial improvements. Even 7B-scale models, when properly trained, outperform many larger proprietary systems, such as GPT-4.1, GPT-4o, and Gemini 2.5 Pro. This indicates that making AI models better research assistants relies more on domain-aligned training with high-quality data than on pretraining scale or general benchmark performance. We release CS-4k and CS-50k in the hope of fostering AI systems as reliable collaborators in CS research.

Large language models (LLMs) have exhibited remarkable capabilities across various domains and tasks, pushing the boundaries of our knowledge in learning and cognition. The latest model, OpenAI's o1, stands out as the first LLM with an internalized chain-of-thought technique using reinforcement learning strategies. While it has demonstrated surprisingly strong capabilities on various general language tasks, its performance in specialized fields such as medicine remains unknown. To this end, this report provides a comprehensive exploration of o1 on different medical scenarios, examining 3 key aspects: understanding, reasoning, and multilinguality. Specifically, our evaluation encompasses 6 tasks using data from 37 medical datasets, including two newly constructed and more challenging question-answering (QA) tasks based on professional medical quizzes from the New England Journal of Medicine (NEJM) and The Lancet. These datasets offer greater clinical relevance compared to standard medical QA benchmarks such as MedQA, translating more effectively into real-world clinical utility. Our analysis of o1 suggests that the enhanced reasoning ability of LLMs may (significantly) benefit their capability to understand various medical instructions and reason through complex clinical scenarios. Notably, o1 surpasses the previous GPT-4 in accuracy by an average of 6.2% and 6.6% across 19 datasets and two newly created complex QA scenarios. But meanwhile, we identify several weaknesses in both the model capability and the existing evaluation protocols, including hallucination, inconsistent multilingual ability, and discrepant metrics for evaluation. We release our raw data and model outputs at https://ucsc-vlaa.github.io/o1_medicine/ for future research.

State-of-the-art performance in QA tasks is currently achieved by systems employing Large Language Models (LLMs), however these models tend to hallucinate information in their responses. One approach focuses on enhancing the generation process by incorporating attribution from the given input to the output. However, the challenge of identifying appropriate attributions and verifying their accuracy against a source is a complex task that requires significant improvements in assessing such systems. We introduce an attribution-oriented Chain-of-Thought reasoning method to enhance the accuracy of attributions. This approach focuses the reasoning process on generating an attribution-centric output. Evaluations on two context-enhanced question-answering datasets using GPT-4 demonstrate improved accuracy and correctness of attributions. In addition, the combination of our method with finetuning enhances the response and attribution accuracy of two smaller LLMs, showing their potential to outperform GPT-4 in some cases.

As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often overly simplistic, allowing models to perform uniformly well, making it difficult to distinguish their capabilities. Additionally, benchmarks typically rely on static question-answer pairs, which models might memorize or guess. To address these limitations, we introduce the Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models using dynamic question templates and improved metrics across multiple disciplines such as mathematics, cryptography, cybersecurity, and computer science. The accompanying DIA-Bench dataset, which includes 150 diverse and challenging task templates with mutable parameters, is presented in various formats such as text, PDFs, compiled binaries, and visual puzzles. Our framework introduces four new metrics to assess a model's reliability and confidence across multiple attempts. These metrics revealed that even simple questions are frequently answered incorrectly when posed in varying forms, highlighting significant gaps in models' reliability. Notably, models like GPT-4o tended to overestimate their mathematical abilities, while ChatGPT-4o demonstrated better decision-making and performance through effective tool usage. We evaluated eight state-of-the-art large language models (LLMs) using DIA-Bench, showing that current models struggle with complex tasks and often display unexpectedly low confidence, even with simpler questions. The DIA framework sets a new standard for assessing not only problem-solving but also a model's adaptive intelligence and ability to assess its own limitations. The dataset is publicly available on our project's website.

We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholarly queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academic queries to assess PaSa performance in more realistic scenarios. Despite being trained on synthetic data, PaSa significantly outperforms existing baselines on RealScholarQuery, including Google, Google Scholar, Google with GPT-4 for paraphrased queries, chatGPT (search-enabled GPT-4o), GPT-o1, and PaSa-GPT-4o (PaSa implemented by prompting GPT-4o). Notably, PaSa-7B surpasses the best Google-based baseline, Google with GPT-4o, by 37.78% in recall@20 and 39.90% in recall@50. It also exceeds PaSa-GPT-4o by 30.36% in recall and 4.25% in precision. Model, datasets, and code are available at https://github.com/bytedance/pasa.

We developed a benchmark set to assess the generalization of state-of-the-art large language models on problems beyond linguistic tasks and evaluate it on a systematic progression of GPT models (GPT-3.5, GPT-4, GPT-4o, GPT-4o-mini). Using simple games like Tic-Tac-Toe, Connect Four, Battleship, and a Shape Recognition Game, all encoded in ASCII, we test strategic capabilities and spatial reasoning, core abilities any artificial intelligence would need to master for solving problems in chemistry. To probe generalization, we introduce two new games for spatial logic: LEGO Connect Language (LCL) and Guess-the-SMILES (GtS), a operationally simple chemistry benchmark. Our results show that GPT models provide meaningful responses for several tasks but, generally, perform poorly. A systematic performance progression with increased model capabilities (GPT-3.5, GPT-4, GPT-4o) is only observed for 4 out of the 7 benchmark tasks. All models consistently struggle with Battleship, LCL, and GtS. This suggests that while GPT models can emulate conversational proficiency and basic rule comprehension, they have limited generalization with respect to strategy and spatial reasoning. Particularly poor performance is observed for interpreting molecular graphs when encoded in ASCII. The results provided by our open-source benchmark suite (https://github.com/BlueVelvetSackOfGoldPotatoes/child-play{ChildPlay GitHub Repository}) caution against claims of emergent intelligence in GPT models, which appear more specialized than general.

In software development, bug report reproduction is a challenging task. This paper introduces ReBL, a novel feedback-driven approach that leverages GPT-4, a large-scale language model, to automatically reproduce Android bug reports. Unlike traditional methods, ReBL bypasses the use of Step to Reproduce (S2R) entities. Instead, it leverages the entire textual bug report and employs innovative prompts to enhance GPT's contextual reasoning. This approach is more flexible and context-aware than the traditional step-by-step entity matching approach, resulting in improved accuracy and effectiveness. In addition to handling crash reports, ReBL has the capability of handling non-crash bug reports. Our evaluation of 96 Android bug reports (73 crash and 23 non-crash) demonstrates that ReBL successfully reproduced 90.63% of these reports, averaging only 74.98 seconds per bug report. Additionally, ReBL outperformed three existing tools in both success rate and speed.

Automated unit test case generation tools facilitate test-driven development and support developers by suggesting tests intended to identify flaws in their code. Existing approaches are usually guided by the test coverage criteria, generating synthetic test cases that are often difficult for developers to read or understand. In this paper we propose AthenaTest, an approach that aims to generate unit test cases by learning from real-world focal methods and developer-written testcases. We formulate unit test case generation as a sequence-to-sequence learning task, adopting a two-step training procedure consisting of denoising pretraining on a large unsupervised Java corpus, and supervised finetuning for a downstream translation task of generating unit tests. We investigate the impact of natural language and source code pretraining, as well as the focal context information surrounding the focal method. Both techniques provide improvements in terms of validation loss, with pretraining yielding 25% relative improvement and focal context providing additional 11.1% improvement. We also introduce Methods2Test, the largest publicly available supervised parallel corpus of unit test case methods and corresponding focal methods in Java, which comprises 780K test cases mined from 91K open-source repositories from GitHub. We evaluate AthenaTest on five defects4j projects, generating 25K passing test cases covering 43.7% of the focal methods with only 30 attempts. We execute the test cases, collect test coverage information, and compare them with test cases generated by EvoSuite and GPT-3, finding that our approach outperforms GPT-3 and has comparable coverage w.r.t. EvoSuite. Finally, we survey professional developers on their preference in terms of readability, understandability, and testing effectiveness of the generated tests, showing overwhelmingly preference towards AthenaTest.

We present FoQA, a Faroese extractive question-answering (QA) dataset with 2,000 samples, created using a semi-automated approach combining Large Language Models (LLMs) and human validation. The dataset was generated from Faroese Wikipedia articles using GPT-4-turbo for initial QA generation, followed by question rephrasing to increase complexity and native speaker validation to ensure quality. We provide baseline performance metrics for FoQA across multiple models, including LLMs and BERT, demonstrating its effectiveness in evaluating Faroese QA performance. The dataset is released in three versions: a validated set of 2,000 samples, a complete set of all 10,001 generated samples, and a set of 2,395 rejected samples for error analysis.

GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June 2023 versions of GPT-3.5 and GPT-4 on four diverse tasks: 1) solving math problems, 2) answering sensitive/dangerous questions, 3) generating code and 4) visual reasoning. We find that the performance and behavior of both GPT-3.5 and GPT-4 can vary greatly over time. For example, GPT-4 (March 2023) was very good at identifying prime numbers (accuracy 97.6%) but GPT-4 (June 2023) was very poor on these same questions (accuracy 2.4%). Interestingly GPT-3.5 (June 2023) was much better than GPT-3.5 (March 2023) in this task. GPT-4 was less willing to answer sensitive questions in June than in March, and both GPT-4 and GPT-3.5 had more formatting mistakes in code generation in June than in March. Overall, our findings shows that the behavior of the same LLM service can change substantially in a relatively short amount of time, highlighting the need for continuous monitoring of LLM quality.

Large Language Models (LLMs) are gaining popularity among software engineers. A crucial aspect of developing effective code generation LLMs is to evaluate these models using a robust benchmark. Evaluation benchmarks with quality issues can provide a false sense of performance. In this work, we conduct the first-of-its-kind study of the quality of prompts within benchmarks used to compare the performance of different code generation models. To conduct this study, we analyzed 3,566 prompts from 9 code generation benchmarks to identify quality issues in them. We also investigated whether fixing the identified quality issues in the benchmarks' prompts affects a model's performance. We also studied memorization issues of the evaluation dataset, which can put into question a benchmark's trustworthiness. We found that code generation evaluation benchmarks mainly focused on Python and coding exercises and had very limited contextual dependencies to challenge the model. These datasets and the developers' prompts suffer from quality issues like spelling and grammatical errors, unclear sentences to express developers' intent, and not using proper documentation style. Fixing all these issues in the benchmarks can lead to a better performance for Python code generation, but not a significant improvement was observed for Java code generation. We also found evidence that GPT-3.5-Turbo and CodeGen-2.5 models may have data contamination issues.

We assessed the performance of commercial Large Language Models (LLMs) GPT-3.5-Turbo and GPT-4 on tasks from the 2023 BioASQ challenge. In Task 11b Phase B, which is focused on answer generation, both models demonstrated competitive abilities with leading systems. Remarkably, they achieved this with simple zero-shot learning, grounded with relevant snippets. Even without relevant snippets, their performance was decent, though not on par with the best systems. Interestingly, the older and cheaper GPT-3.5-Turbo system was able to compete with GPT-4 in the grounded Q&A setting on factoid and list answers. In Task 11b Phase A, focusing on retrieval, query expansion through zero-shot learning improved performance, but the models fell short compared to other systems. The code needed to rerun these experiments is available through GitHub.

We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. We ensure that the questions are high-quality and extremely difficult: experts who have or are pursuing PhDs in the corresponding domains reach 65% accuracy (74% when discounting clear mistakes the experts identified in retrospect), while highly skilled non-expert validators only reach 34% accuracy, despite spending on average over 30 minutes with unrestricted access to the web (i.e., the questions are "Google-proof"). The questions are also difficult for state-of-the-art AI systems, with our strongest GPT-4 based baseline achieving 39% accuracy. If we are to use future AI systems to help us answer very hard questions, for example, when developing new scientific knowledge, we need to develop scalable oversight methods that enable humans to supervise their outputs, which may be difficult even if the supervisors are themselves skilled and knowledgeable. The difficulty of GPQA both for skilled non-experts and frontier AI systems should enable realistic scalable oversight experiments, which we hope can help devise ways for human experts to reliably get truthful information from AI systems that surpass human capabilities.

Code Large Language Models (LLMs) enhance software development efficiency by automatically generating code and documentation in response to user requirements. However, code LLMs cannot synthesize specialized programs when tasked with IoT applications that require domain knowledge. While Retrieval-Augmented Generation (RAG) offers a promising solution by fetching relevant domain knowledge, it necessitates powerful cloud LLMs (e.g., GPT-4) to process user requirements and retrieved contents, which raises significant privacy concerns. This approach also suffers from unstable networks and prohibitive LLM query costs. Moreover, it is challenging to ensure the correctness and relevance of the fetched contents. To address these issues, we propose GPIoT, a code generation system for IoT applications by fine-tuning locally deployable Small Language Models (SLMs) on IoT-specialized datasets. SLMs have smaller model sizes, allowing efficient local deployment and execution to mitigate privacy concerns and network uncertainty. Furthermore, by fine-tuning the SLMs with our IoT-specialized datasets, the SLMs' ability to synthesize IoT-related programs can be substantially improved. To evaluate GPIoT's capability in synthesizing programs for IoT applications, we develop a benchmark, IoTBench. Extensive experiments and user trials demonstrate the effectiveness of GPIoT in generating IoT-specialized code, outperforming state-of-the-art code LLMs with an average task accuracy increment of 64.7% and significant improvements in user satisfaction.

We introduce a multi-stage prompting approach (MSP) for the generation of multiple choice questions (MCQs), harnessing the capabilities of GPT models such as text-davinci-003 and GPT-4, renowned for their excellence across various NLP tasks. Our approach incorporates the innovative concept of chain-of-thought prompting, a progressive technique in which the GPT model is provided with a series of interconnected cues to guide the MCQ generation process. Automated evaluations consistently demonstrate the superiority of our proposed MSP method over the traditional single-stage prompting (SSP) baseline, resulting in the production of high-quality distractors. Furthermore, the one-shot MSP technique enhances automatic evaluation results, contributing to improved distractor generation in multiple languages, including English, German, Bengali, and Hindi. In human evaluations, questions generated using our approach exhibit superior levels of grammaticality, answerability, and difficulty, highlighting its efficacy in various languages.

We present FIMO, an innovative dataset comprising formal mathematical problem statements sourced from the International Mathematical Olympiad (IMO) Shortlisted Problems. Designed to facilitate advanced automated theorem proving at the IMO level, FIMO is currently tailored for the Lean formal language. It comprises 149 formal problem statements, accompanied by both informal problem descriptions and their corresponding LaTeX-based informal proofs. Through initial experiments involving GPT-4, our findings underscore the existing limitations in current methodologies, indicating a substantial journey ahead before achieving satisfactory IMO-level automated theorem proving outcomes.

The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent version updates while maintaining compatibility with previous versions. Existing code completion benchmarks often overlook this dynamic aspect, and the one that does consider it relies on static code prediction tasks without execution-based evaluation, offering a limited perspective on a model's practical usability. To address this gap, we introduce \GitChameleon{}, a novel, manually curated dataset comprising 116 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. is designed to rigorously assess the ability of modern large language models (LLMs) to generate version-specific code that is not only syntactically correct but also functionally accurate upon execution. Our comprehensive evaluations reveal that state-of-the-art LLMs struggle with this task; for instance, GPT-4o achieves a pass@10 of only 39.9\% (43.7\% when provided with error feedback), highlighting the complexity of the problem and the limitations of current models. By providing an execution-based benchmark that emphasizes the dynamic nature of code libraries, serves as a critical tool to advance the development of more adaptable and reliable code generation models. For facilitation for further exploration of version-conditioned code generation, we make our code repository publicly accessible at https://github.com/NizarIslah/GitChameleon.

We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-world scenarios, GPT-4 exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers. GPT-4 is a Transformer-based model pre-trained to predict the next token in a document. The post-training alignment process results in improved performance on measures of factuality and adherence to desired behavior. A core component of this project was developing infrastructure and optimization methods that behave predictably across a wide range of scales. This allowed us to accurately predict some aspects of GPT-4's performance based on models trained with no more than 1/1,000th the compute of GPT-4.

Generative AI has made rapid advancements in recent years, achieving unprecedented capabilities in multimodal understanding and code generation. This can enable a new paradigm of front-end development, in which multimodal LLMs might directly convert visual designs into code implementations. In this work, we formalize this as a Design2Code task and conduct comprehensive benchmarking. Specifically, we manually curate a benchmark of 484 diverse real-world webpages as test cases and develop a set of automatic evaluation metrics to assess how well current multimodal LLMs can generate the code implementations that directly render into the given reference webpages, given the screenshots as input. We also complement automatic metrics with comprehensive human evaluations. We develop a suite of multimodal prompting methods and show their effectiveness on GPT-4V and Gemini Pro Vision. We further finetune an open-source Design2Code-18B model that successfully matches the performance of Gemini Pro Vision. Both human evaluation and automatic metrics show that GPT-4V performs the best on this task compared to other models. Moreover, annotators think GPT-4V generated webpages can replace the original reference webpages in 49% of cases in terms of visual appearance and content; and perhaps surprisingly, in 64% of cases GPT-4V generated webpages are considered better than the original reference webpages. Our fine-grained break-down metrics indicate that open-source models mostly lag in recalling visual elements from the input webpages and in generating correct layout designs, while aspects like text content and coloring can be drastically improved with proper finetuning.

A code generation model generates code by taking a prompt from a code comment, existing code, or a combination of both. Although code generation models (e.g. GitHub Copilot) are increasingly being adopted in practice, it is unclear whether they can successfully be used for unit test generation without fine-tuning. We investigated how well three generative models (Codex, GPT-3.5-Turbo, and StarCoder) can generate test cases to fill this gap. We used two benchmarks (HumanEval and Evosuite SF110) to investigate the context generation's effect in the unit test generation process. We evaluated the models based on compilation rates, test correctness, coverage, and test smells. We found that the Codex model achieved above 80% coverage for the HumanEval dataset, but no model had more than 2% coverage for the EvoSuite SF110 benchmark. The generated tests also suffered from test smells, such as Duplicated Asserts and Empty Tests.

We present ExAct, a new video-language benchmark for expert-level understanding of skilled physical human activities. Our new benchmark contains 3521 expert-curated video question-answer pairs spanning 11 physical activities in 6 domains: Sports, Bike Repair, Cooking, Health, Music, and Dance. ExAct requires the correct answer to be selected from five carefully designed candidate options, thus necessitating a nuanced, fine-grained, expert-level understanding of physical human skills. Evaluating the recent state-of-the-art VLMs on ExAct reveals a substantial performance gap relative to human expert performance. Specifically, the best-performing GPT-4o model achieves only 44.70% accuracy, well below the 82.02% attained by trained human specialists/experts. We believe that ExAct will be beneficial for developing and evaluating VLMs capable of precise understanding of human skills in various physical and procedural domains. Dataset and code are available at https://texaser.github.io/exact_project_page/

Large Language Models (LLMs) have proved effective and efficient in generating code, leading to their utilization within the hardware design process. Prior works evaluating LLMs' abilities for register transfer level code generation solely focus on functional correctness. However, the creativity associated with these LLMs, or the ability to generate novel and unique solutions, is a metric not as well understood, in part due to the challenge of quantifying this quality. To address this research gap, we present CreativeEval, a framework for evaluating the creativity of LLMs within the context of generating hardware designs. We quantify four creative sub-components, fluency, flexibility, originality, and elaboration, through various prompting and post-processing techniques. We then evaluate multiple popular LLMs (including GPT models, CodeLlama, and VeriGen) upon this creativity metric, with results indicating GPT-3.5 as the most creative model in generating hardware designs.

In recent years, groundbreaking advancements in natural language processing have culminated in the emergence of powerful large language models (LLMs), which have showcased remarkable capabilities across a vast array of domains, including the understanding, generation, and translation of natural language, and even tasks that extend beyond language processing. In this report, we delve into the performance of LLMs within the context of scientific discovery, focusing on GPT-4, the state-of-the-art language model. Our investigation spans a diverse range of scientific areas encompassing drug discovery, biology, computational chemistry (density functional theory (DFT) and molecular dynamics (MD)), materials design, and partial differential equations (PDE). Evaluating GPT-4 on scientific tasks is crucial for uncovering its potential across various research domains, validating its domain-specific expertise, accelerating scientific progress, optimizing resource allocation, guiding future model development, and fostering interdisciplinary research. Our exploration methodology primarily consists of expert-driven case assessments, which offer qualitative insights into the model's comprehension of intricate scientific concepts and relationships, and occasionally benchmark testing, which quantitatively evaluates the model's capacity to solve well-defined domain-specific problems. Our preliminary exploration indicates that GPT-4 exhibits promising potential for a variety of scientific applications, demonstrating its aptitude for handling complex problem-solving and knowledge integration tasks. Broadly speaking, we evaluate GPT-4's knowledge base, scientific understanding, scientific numerical calculation abilities, and various scientific prediction capabilities.

The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter passing to guide the agent's execution module in performing multi-step tool-calling tasks with high stability. In evaluations conducted within a real-world enterprise scenario, Routine significantly increases the execution accuracy in model tool calls, increasing the performance of GPT-4o from 41.1% to 96.3%, and Qwen3-14B from 32.6% to 83.3%. We further constructed a Routine-following training dataset and fine-tuned Qwen3-14B, resulting in an accuracy increase to 88.2% on scenario-specific evaluations, indicating improved adherence to execution plans. In addition, we employed Routine-based distillation to create a scenario-specific, multi-step tool-calling dataset. Fine-tuning on this distilled dataset raised the model's accuracy to 95.5%, approaching GPT-4o's performance. These results highlight Routine's effectiveness in distilling domain-specific tool-usage patterns and enhancing model adaptability to new scenarios. Our experimental results demonstrate that Routine provides a practical and accessible approach to building stable agent workflows, accelerating the deployment and adoption of agent systems in enterprise environments, and advancing the technical vision of AI for Process.

Evaluating language models fairly is becoming harder as static benchmarks available on the internet risk contamination by training data. This makes it unclear whether models are truly reasoning or just recalling answers. In this paper, we introduce BeyondBench, an evaluation framework that avoids this problem by using algorithmic problem generation. Unlike traditional benchmarks that risk contamination from internet-scale training data, BeyondBench creates mathematically grounded problems on the fly, ensuring each test remains fresh and uncontaminated. Our framework covers 44 algorithmic tasks with a total of 117 variations, grouped into three difficulty levels: the Easy Suite (29 tasks) for basic arithmetic and statistics, the Medium Suite (5 tasks, 49 variations) for sequence patterns and reasoning, and the Hard Suite (10 tasks, 68 variations) tackling NP-complete and constraint satisfaction problems. Each task generates problems from a combinatorial space larger than 10^15 unique instances, with solutions verified deterministically by mathematical proofs. We evaluated 101 language models, including 85 open-source and 16 closed-source models, spanning sizes from 0.5B to 141B parameters and multiple quantization schemes. Our results show consistent reasoning deficiencies across model families, with performance degrading sharply as problem complexity increases from polynomial to exponential. In our Hard Suite evaluations, models such as Gemini-2.5-pro, Llama-3.3-70B, and Qwen2.5-72B achieved average accuracies of 56.38%, 26.91%, and 33.60%, respectively. Moreover, we observe that performance drops drastically without tool usage, with GPT-5, GPT-5-mini, and GPT-5-nano showing a decline of 16.81%, 28.05%, and 47.59% accuracy on the hard suite. Our leaderboard is publicly available at https://ctrl-gaurav.github.io/BeyondBench/

Despite advances in reasoning and planning of R1-like models, Large Language Models (LLMs) still struggle with tasks requiring precise computation, symbolic manipulation, optimization, and algorithmic reasoning, in which textual reasoning lacks the rigor of code execution. A key challenge is enabling LLMs to decide when to use textual reasoning versus code generation. While OpenAI trains models to invoke a Code Interpreter as needed, public research lacks guidance on aligning pre-trained LLMs to effectively leverage code and generalize across diverse tasks. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL) to autonomously generate multiple code queries during step-by-step reasoning. We curate 144 reasoning and planning tasks (107 for training, 37 for testing), each with over 200 diverse questions. We fine-tune Qwen-2.5 models (3B/7B/14B) using various SFT and RL strategies, investigating different answer formats, reasoning vs. non-reasoning models, cold vs. warm starts, GRPO vs. PPO, and masked vs. unmasked code outputs. Unlike prior RL work on narrow domains, we find that Code Interpreter training is significantly harder due to high task diversity and expensive code execution, highlighting the critical role of the SFT stage. Our final model, R1-CI-14B, improves average accuracy on the 37 test tasks from 44.0\% to 64.1\%, outperforming GPT-4o (text-only: 58.6\%) and approaching GPT-4o with Code Interpreter (70.9\%), with the emergent self-checking behavior via code generation. Datasets, Codes, and Models are available at https://github.com/yongchao98/R1-Code-Interpreter and https://huggingface.co/yongchao98.

Establishing fair and robust benchmarks is essential for evaluating intelligent code generation by large language models (LLMs). Our survey of 35 existing benchmarks uncovers three major imbalances: 85.7% focus on a single programming language; 94.3% target only function-level or statement-level tasks; and over 80% include fewer than ten test cases on average. To address these gaps, we propose MultiOOP, a multi-language object-oriented programming benchmark covering six popular languages (Python, PHP, C++, C#, Java, JavaScript) with 267 tasks per language. We design a translator that extends an existing single-language OOP benchmark and the pass@o metric to a multilingual setting. Moreover, we propose an automated framework for augmenting test cases to ensure the reliability of the evaluation results. We evaluate 14 mainstream LLMs under zero-shot prompting and report three key findings: 1) Substantial performance degradation: pass@1 scores on MultiOOP drop by up to 65.6 percentage points compared to function-level tasks (e.g., HumanEval). 2) Cross-language variability: GPT-4o mini achieves pass@1 of 48.06% in Python but only 0.12%-15.26% in other languages, indicating limited multilingual generalization. 3) Conceptual gaps: pass@o scores are consistently 1.1-19.2 points lower than pass@k, demonstrating that LLMs often generate executable code without fully capturing core OOP concepts. Our benchmark, metric extensions, and evaluation scripts will be publicly released to foster a more balanced and comprehensive assessment of LLMs in object-oriented code generation. Our code and data will be released at https://github.com/alphadl/OOP-eval and https://huggingface.co/datasets/codeai-dteam/MultiOOP respectively.

We analyzed effectiveness of three generative pre-trained transformer (GPT) models in answering multiple-choice question (MCQ) assessments, often involving short snippets of code, from introductory and intermediate programming courses at the postsecondary level. This emerging technology stirs countless discussions of its potential uses (e.g., exercise generation, code explanation) as well as misuses in programming education (e.g., cheating). However, the capabilities of GPT models and their limitations to reason about and/or analyze code in educational settings have been under-explored. We evaluated several OpenAI's GPT models on formative and summative MCQ assessments from three Python courses (530 questions). We found that MCQs containing code snippets are not answered as successfully as those that only contain natural language. While questions requiring to fill-in a blank in the code or completing a natural language statement about the snippet are handled rather successfully, MCQs that require analysis and/or reasoning about the code (e.g., what is true/false about the snippet, or what is its output) appear to be the most challenging. These findings can be leveraged by educators to adapt their instructional practices and assessments in programming courses, so that GPT becomes a valuable assistant for a learner as opposed to a source of confusion and/or potential hindrance in the learning process.

We curate a comprehensive dataset of 4,550 questions and solutions from problem sets, midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and Computer Science (EECS) courses required for obtaining a degree. We evaluate the ability of large language models to fulfill the graduation requirements for any MIT major in Mathematics and EECS. Our results demonstrate that GPT-3.5 successfully solves a third of the entire MIT curriculum, while GPT-4, with prompt engineering, achieves a perfect solve rate on a test set excluding questions based on images. We fine-tune an open-source large language model on this dataset. We employ GPT-4 to automatically grade model responses, providing a detailed performance breakdown by course, question, and answer type. By embedding questions in a low-dimensional space, we explore the relationships between questions, topics, and classes and discover which questions and classes are required for solving other questions and classes through few-shot learning. Our analysis offers valuable insights into course prerequisites and curriculum design, highlighting language models' potential for learning and improving Mathematics and EECS education.

Mathematical geometric problem solving (GPS) often requires effective integration of multimodal information and verifiable logical coherence. Despite the fast development of large language models in general problem solving, it remains unresolved regarding with both methodology and benchmarks, especially given the fact that exiting synthetic GPS benchmarks are often not self-verified and contain noise and self-contradicted information due to the illusion of LLMs. In this paper, we propose a scalable data engine called TrustGeoGen for problem generation, with formal verification to provide a principled benchmark, which we believe lays the foundation for the further development of methods for GPS. The engine synthesizes geometric data through four key innovations: 1) multimodal-aligned generation of diagrams, textual descriptions, and stepwise solutions; 2) formal verification ensuring rule-compliant reasoning paths; 3) a bootstrapping mechanism enabling complexity escalation via recursive state generation and 4) our devised GeoExplore series algorithms simultaneously produce multi-solution variants and self-reflective backtracking traces. By formal logical verification, TrustGeoGen produces GeoTrust-200K dataset with guaranteed modality integrity, along with GeoTrust-test testset. Experiments reveal the state-of-the-art models achieve only 49.17\% accuracy on GeoTrust-test, demonstrating its evaluation stringency. Crucially, models trained on GeoTrust achieve OOD generalization on GeoQA, significantly reducing logical inconsistencies relative to pseudo-label annotated by OpenAI-o1. Our code is available at https://github.com/Alpha-Innovator/TrustGeoGen

Reinforcement learning (RL) has significantly advanced code generation for large language models (LLMs). However, current paradigms rely on outcome-based rewards from test cases, neglecting the quality of the intermediate reasoning process. While supervising the reasoning process directly is a promising direction, it is highly susceptible to reward hacking, where the policy model learns to exploit the reasoning reward signal without improving final outcomes. To address this, we introduce a unified framework that can effectively incorporate the quality of the reasoning process during RL. First, to enable reasoning evaluation, we develop LCB-RB, a benchmark comprising preference pairs of superior and inferior reasoning processes. Second, to accurately score reasoning quality, we introduce an Optimized-Degraded based (OD-based) method for reward model training. This method generates high-quality preference pairs by systematically optimizing and degrading initial reasoning paths along curated dimensions of reasoning quality, such as factual accuracy, logical rigor, and coherence. A 7B parameter reward model with this method achieves state-of-the-art (SOTA) performance on LCB-RB and generalizes well to other benchmarks. Finally, we introduce Posterior-GRPO (P-GRPO), a novel RL method that conditions process-based rewards on task success. By selectively applying rewards to the reasoning processes of only successful outcomes, P-GRPO effectively mitigates reward hacking and aligns the model's internal reasoning with final code correctness. A 7B parameter model with P-GRPO achieves superior performance across diverse code generation tasks, outperforming outcome-only baselines by 4.5%, achieving comparable performance to GPT-4-Turbo. We further demonstrate the generalizability of our approach by extending it to mathematical tasks. Our models, dataset, and code are publicly available.

Interests in the automatic generation of cooking recipes have been growing steadily over the past few years thanks to a large amount of online cooking recipes. We present RecipeGPT, a novel online recipe generation and evaluation system. The system provides two modes of text generations: (1) instruction generation from given recipe title and ingredients; and (2) ingredient generation from recipe title and cooking instructions. Its back-end text generation module comprises a generative pre-trained language model GPT-2 fine-tuned on a large cooking recipe dataset. Moreover, the recipe evaluation module allows the users to conveniently inspect the quality of the generated recipe contents and store the results for future reference. RecipeGPT can be accessed online at https://recipegpt.org/.

Despite recent advances in text-to-3D generative methods, there is a notable absence of reliable evaluation metrics. Existing metrics usually focus on a single criterion each, such as how well the asset aligned with the input text. These metrics lack the flexibility to generalize to different evaluation criteria and might not align well with human preferences. Conducting user preference studies is an alternative that offers both adaptability and human-aligned results. User studies, however, can be very expensive to scale. This paper presents an automatic, versatile, and human-aligned evaluation metric for text-to-3D generative models. To this end, we first develop a prompt generator using GPT-4V to generate evaluating prompts, which serve as input to compare text-to-3D models. We further design a method instructing GPT-4V to compare two 3D assets according to user-defined criteria. Finally, we use these pairwise comparison results to assign these models Elo ratings. Experimental results suggest our metric strongly align with human preference across different evaluation criteria.

Code generation has emerged as a key task to automate software development by converting high-level descriptions into executable code. Large language models (LLMs) excel at this but depend heavily on input prompt quality.Manual prompt engineering can be time-consuming and inconsistent, limiting LLM effectiveness. This paper introduces Prochemy, an innovative method for automatically refining prompts to boost code generation. Prochemy overcomes manual prompt limitations by automating optimization, ensuring consistency during inference, and supporting multi-agent systems.It iteratively refines prompts based on model performance, using an optimized final prompt for improved consistency across tasks. We tested Prochemy on natural language-based code generation and translation tasks using three LLM series. Results indicate Prochemy enhances existing methods, improving performance by 5.0% for GPT-3.5-Turbo and 1.9% for GPT-4o over zero-shot baselines on HumanEval. In state-of-the-art LDB, Prochemy + LDB surpasses standalone methods by 1.2-1.8%. For code translation, Prochemy boosts GPT-4o's Java-to-Python (AVATAR) performance from 74.5 to 84.1 (+12.9%) and Python-to-Java from 66.8 to 78.2 (+17.1%). Moreover, Prochemy maintains strong performance when integrated with the o1-mini model, validating its efficacy in code tasks. Designed as plug-and-play, Prochemy optimizes prompts with minimal human input, bridging the gap between simple prompts and complex frameworks.

There is an increasing body of work using Large Language Models (LLMs) as agents for orchestrating workflows and making decisions in domains that require planning and multi-step reasoning. As a result, it is imperative to evaluate LLMs on core skills required for planning. In this work, we present ACPBench, a benchmark for evaluating the reasoning tasks in the field of planning. The benchmark consists of 7 reasoning tasks over 13 planning domains. The collection is constructed from planning domains described in a formal language. This allows us to synthesize problems with provably correct solutions across many tasks and domains. Further, it allows us the luxury of scale without additional human effort, i.e., many additional problems can be created automatically. Our extensive evaluation of 22 open-sourced and frontier LLMs highlight the significant gap in the reasoning capability of the LLMs. The average accuracy of one of the best-performing frontier LLMs -- GPT-4o on these tasks can fall as low as 52.50% ACPBench collection is available at https://ibm.github.io/ACPBench.

With the rapid advancement of large language models (LLMs), there is a pressing need for a comprehensive evaluation suite to assess their capabilities and limitations. Existing LLM leaderboards often reference scores reported in other papers without consistent settings and prompts, which may inadvertently encourage cherry-picking favored settings and prompts for better results. In this work, we introduce GPT-Fathom, an open-source and reproducible LLM evaluation suite built on top of OpenAI Evals. We systematically evaluate 10+ leading LLMs as well as OpenAI's legacy models on 20+ curated benchmarks across 7 capability categories, all under aligned settings. Our retrospective study on OpenAI's earlier models offers valuable insights into the evolutionary path from GPT-3 to GPT-4. Currently, the community is eager to know how GPT-3 progressively improves to GPT-4, including technical details like whether adding code data improves LLM's reasoning capability, which aspects of LLM capability can be improved by SFT and RLHF, how much is the alignment tax, etc. Our analysis sheds light on many of these questions, aiming to improve the transparency of advanced LLMs.

Large language models (LLMs) often struggle with maintaining accuracy across a sequence of intermediate reasoning steps in mathematical reasoning, leading to error propagation that undermines the final result. The current methodology to mitigate this issue primarily involves using a verifier model to assess the correctness of generated solution candidates, focusing either on the overall reasoning path or on an incomplete reasoning path. By rethinking this approach, we argue that assessing potentials of incomplete reasoning paths could be more advantageous as it guides towards correct final answers, transforming the task into a planning problem. Our proposed verifier, the Outcome-supervision Value Model (OVM), employs outcome supervision for training, offering an efficient and intuitive method for planning by prioritizing steps that lead to accurate conclusions over mere per-step correctness. Furthermore, the OVM eschews the need for labor-intensive annotations on step-level correctness, enhancing its scalability. Our experiments on two multi-step mathematical reasoning datasets, GSM8K and Game of 24, demonstrate the superior performance of the OVM model. Notably, in GSM8K, our OVM-7B model achieves state-of-the-art results among LLMs up to 13B parameters; especially it does not utilize GPT-4 or code execution. These findings offer a novel perspective on the role of outcome supervision in training verifiers for multi-step reasoning tasks and provide theoretical justification for its advantage in value estimation for planning.

ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural language question answering using its own knowledge. Therefore, there is growing interest in exploring whether ChatGPT can replace traditional knowledge-based question answering (KBQA) models. Although there have been some works analyzing the question answering performance of ChatGPT, there is still a lack of large-scale, comprehensive testing of various types of complex questions to analyze the limitations of the model. In this paper, we present a framework that follows the black-box testing specifications of CheckList proposed by Ribeiro et. al. We evaluate ChatGPT and its family of LLMs on eight real-world KB-based complex question answering datasets, which include six English datasets and two multilingual datasets. The total number of test cases is approximately 190,000. In addition to the GPT family of LLMs, we also evaluate the well-known FLAN-T5 to identify commonalities between the GPT family and other LLMs. The dataset and code are available at https://github.com/tan92hl/Complex-Question-Answering-Evaluation-of-GPT-family.git

Evaluating the general abilities of foundation models to tackle human-level tasks is a vital aspect of their development and application in the pursuit of Artificial General Intelligence (AGI). Traditional benchmarks, which rely on artificial datasets, may not accurately represent human-level capabilities. In this paper, we introduce AGIEval, a novel benchmark specifically designed to assess foundation model in the context of human-centric standardized exams, such as college entrance exams, law school admission tests, math competitions, and lawyer qualification tests. We evaluate several state-of-the-art foundation models, including GPT-4, ChatGPT, and Text-Davinci-003, using this benchmark. Impressively, GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam. This demonstrates the extraordinary performance of contemporary foundation models. In contrast, we also find that GPT-4 is less proficient in tasks that require complex reasoning or specific domain knowledge. Our comprehensive analyses of model capabilities (understanding, knowledge, reasoning, and calculation) reveal these models' strengths and limitations, providing valuable insights into future directions for enhancing their general capabilities. By concentrating on tasks pertinent to human cognition and decision-making, our benchmark delivers a more meaningful and robust evaluation of foundation models' performance in real-world scenarios. The data, code, and all model outputs are released in https://github.com/microsoft/AGIEval.

While Large Language Models (LLMs) have demonstrated significant advancements in reasoning and agent-based problem-solving, current evaluation methodologies fail to adequately assess their capabilities: existing benchmarks either rely on closed-ended questions prone to saturation and memorization, or subjective comparisons that lack consistency and rigor. In this work, we introduce HeuriGym, an agentic framework designed for evaluating heuristic algorithms generated by LLMs for combinatorial optimization problems, characterized by clearly defined objectives and expansive solution spaces. HeuriGym empowers LLMs to propose heuristics, receive evaluative feedback via code execution, and iteratively refine their solutions. We evaluate nine state-of-the-art models on nine problems across domains such as computer systems, logistics, and biology, exposing persistent limitations in tool use, planning, and adaptive reasoning. To quantify performance, we propose the Quality-Yield Index (QYI), a metric that captures both solution pass rate and quality. Even top models like GPT-o4-mini-high and Gemini-2.5-Pro attain QYI scores of only 0.6, well below the expert baseline of 1. Our open-source benchmark aims to guide the development of LLMs toward more effective and realistic problem-solving in scientific and engineering domains.

Large Language Models (LLMs) have transformed natural language processing, yet improving their problem-solving capabilities, particularly for complex, reasoning-intensive tasks, remains a persistent challenge. This paper introduces the REAP (Reflection, Explicit Problem Deconstruction, and Advanced Prompting) method, an innovative approach within the dynamic context generation framework. REAP guides LLMs through reflection on the query, deconstructing it into manageable components, and generating relevant context to enhance the solution process. We evaluated REAP using a dataset designed to expose LLM limitations, comparing zero-shot prompting with REAP-enhanced prompts across six state-of-the-art models: OpenAI's o1-preview, o1-mini, GPT-4o, GPT-4o-mini, Google's Gemini 1.5 Pro, and Claude 3.5 Sonnet. The results demonstrate notable performance gains, with o1-mini improving by 40.97%, GPT-4o by 66.26%, and GPT-4o-mini by 112.93%. Despite the already strong baseline performance of OpenAI's o1-preview, modest gains were observed. Beyond performance improvements, REAP offers a cost-effective solution; for example, GPT-4o-mini, which is approximately 100 times cheaper than o1-preview, delivered competitive results. REAP also improves the clarity of model outputs, making it easier for humans to understand the reasoning behind the results and simplifying the process of identifying and addressing any issues. These findings demonstrate REAP's potential to greatly improve the capabilities of LLMs, providing both better performance and increased cost-efficiency across a wide range of applications.

Current text-to-image generation models often struggle to follow textual instructions, especially the ones requiring spatial reasoning. On the other hand, Large Language Models (LLMs), such as GPT-4, have shown remarkable precision in generating code snippets for sketching out text inputs graphically, e.g., via TikZ. In this work, we introduce Control-GPT to guide the diffusion-based text-to-image pipelines with programmatic sketches generated by GPT-4, enhancing their abilities for instruction following. Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e.g., ControlNet) to generate photo-realistic images. One major challenge to training our pipeline is the lack of a dataset containing aligned text, images, and sketches. We address the issue by converting instance masks in existing datasets into polygons to mimic the sketches used at test time. As a result, Control-GPT greatly boosts the controllability of image generation. It establishes a new state-of-art on the spatial arrangement and object positioning generation and enhances users' control of object positions, sizes, etc., nearly doubling the accuracy of prior models. Our work, as a first attempt, shows the potential for employing LLMs to enhance the performance in computer vision tasks.

Evaluating instruction following capabilities for multimodal, multi-turn dialogue is challenging. With potentially multiple instructions in the input model context, the task is time-consuming for human raters and we show LLM based judges are biased towards answers from the same model. We propose MMMT-IF, an image based multi-turn Q&A evaluation set with added global instructions between questions, constraining the answer format. This challenges models to retrieve instructions dispersed across long dialogues and reason under instruction constraints. All instructions are objectively verifiable through code execution. We introduce the Programmatic Instruction Following (PIF) metric to measure the fraction of the instructions that are correctly followed while performing a reasoning task. The PIF-N-K set of metrics further evaluates robustness by measuring the fraction of samples in a corpus where, for each sample, at least K out of N generated model responses achieve a PIF score of one. The PIF metric aligns with human instruction following ratings, showing 60 percent correlation. Experiments show Gemini 1.5 Pro, GPT-4o, and Claude 3.5 Sonnet, have a PIF metric that drops from 0.81 on average at turn 1 across the models, to 0.64 at turn 20. Across all turns, when each response is repeated 4 times (PIF-4-4), GPT-4o and Gemini successfully follow all instructions only 11% of the time. When all the instructions are also appended to the end of the model input context, the PIF metric improves by 22.3 points on average, showing that the challenge with the task lies not only in following the instructions, but also in retrieving the instructions spread out in the model context. We plan to open source the MMMT-IF dataset and metric computation code.

Large Language Models (LLMs) achieve superior performance through training-time scaling, and test-time scaling further enhances their capabilities by conducting effective reasoning during inference. However, as the scale of reasoning increases, existing test-time scaling methods suffer from accumulated historical information, which not only wastes computational resources but also interferes with effective reasoning. To address this issue, we observe that complex reasoning progress is often achieved by solving a sequence of independent subquestions, each being self-contained and verifiable. These subquestions are essentially atomic questions, relying primarily on their current state rather than accumulated history, similar to the memoryless transitions in a Markov process. Based on this observation, we propose Atom of Thoughts (AoT), where each state transition in the reasoning process consists of decomposing the current question into a dependency-based directed acyclic graph and contracting its subquestions, forming a new atomic question state. This iterative decomposition-contraction process continues until reaching directly solvable atomic questions, naturally realizing Markov transitions between question states. Furthermore, these atomic questions can be seamlessly integrated into existing test-time scaling methods, enabling AoT to serve as a plug-in enhancement for improving reasoning capabilities. Experiments across six benchmarks demonstrate the effectiveness of AoT both as a standalone framework and a plug-in enhancement. Notably, on HotpotQA, when applied to gpt-4o-mini, AoT achieves an 80.6% F1 score, surpassing o3-mini by 3.4% and DeepSeek-R1 by 10.6%. The code will be available at https://github.com/qixucen/atom.

Testing is an integral part of the software development process. Yet, writing tests is time-consuming and therefore often neglected. Classical test generation tools such as EvoSuite generate behavioral test suites by optimizing for coverage, but tend to produce tests that are hard to understand. Language models trained on code can generate code that is highly similar to that written by humans, but current models are trained to generate each file separately, as is standard practice in natural language processing, and thus fail to consider the code-under-test context when producing a test file. In this work, we propose the Aligned Code And Tests Language Model (CAT-LM), a GPT-style language model with 2.7 Billion parameters, trained on a corpus of Python and Java projects. We utilize a novel pretraining signal that explicitly considers the mapping between code and test files when available. We also drastically increase the maximum sequence length of inputs to 8,192 tokens, 4x more than typical code generation models, to ensure that the code context is available to the model when generating test code. We analyze its usefulness for realistic applications, showing that sampling with filtering (e.g., by compilability, coverage) allows it to efficiently produce tests that achieve coverage similar to ones written by developers while resembling their writing style. By utilizing the code context, CAT-LM generates more valid tests than even much larger language models trained with more data (CodeGen 16B and StarCoder) and substantially outperforms a recent test-specific model (TeCo) at test completion. Overall, our work highlights the importance of incorporating software-specific insights when training language models for code and paves the way to more powerful automated test generation.

Multiple-choice question (MCQ) datasets like Massive Multitask Language Understanding (MMLU) are widely used to evaluate the commonsense, understanding, and problem-solving abilities of large language models (LLMs). However, the open-source nature of these benchmarks and the broad sources of training data for LLMs have inevitably led to benchmark contamination, resulting in unreliable evaluation results. To alleviate this issue, we propose a contamination-free and more challenging MCQ benchmark called MMLU-CF. This benchmark reassesses LLMs' understanding of world knowledge by averting both unintentional and malicious data leakage. To avoid unintentional data leakage, we source data from a broader domain and design three decontamination rules. To prevent malicious data leakage, we divide the benchmark into validation and test sets with similar difficulty and subject distributions. The test set remains closed-source to ensure reliable results, while the validation set is publicly available to promote transparency and facilitate independent verification. Our evaluation of mainstream LLMs reveals that the powerful GPT-4o achieves merely a 5-shot score of 73.4% and a 0-shot score of 71.9% on the test set, which indicates the effectiveness of our approach in creating a more rigorous and contamination-free evaluation standard. The GitHub repository is available at https://github.com/microsoft/MMLU-CF and the dataset refers to https://huggingface.co/datasets/microsoft/MMLU-CF.

We present CRUXEval (Code Reasoning, Understanding, and eXecution Evaluation), a benchmark consisting of 800 Python functions (3-13 lines). Each function comes with an input-output pair, leading to two natural tasks: input prediction and output prediction. First, we propose a generic recipe for generating our execution benchmark which can be used to create future variation of the benchmark. Second, we evaluate twenty code models on our benchmark and discover that many recent high-scoring models on HumanEval do not show the same improvements on our benchmark. Third, we show that simple CoT and fine-tuning schemes can improve performance on our benchmark but remain far from solving it. The best setup, GPT-4 with chain of thought (CoT), achieves a pass@1 of 75% and 81% on input and output prediction, respectively. In contrast, Code Llama 34B achieves a pass@1 of 50% and 46% on input and output prediction, highlighting the gap between open and closed source models. As no model is close to acing CRUXEval, we provide examples of consistent GPT-4 failures on simple programs as a lens into its code reasoning capabilities and areas for improvement.

Unit testing is an essential activity in software development for verifying the correctness of software components. However, manually writing unit tests is challenging and time-consuming. The emergence of Large Language Models (LLMs) offers a new direction for automating unit test generation. Existing research primarily focuses on closed-source LLMs (e.g., ChatGPT and CodeX) with fixed prompting strategies, leaving the capabilities of advanced open-source LLMs with various prompting settings unexplored. Particularly, open-source LLMs offer advantages in data privacy protection and have demonstrated superior performance in some tasks. Moreover, effective prompting is crucial for maximizing LLMs' capabilities. In this paper, we conduct the first empirical study to fill this gap, based on 17 Java projects, five widely-used open-source LLMs with different structures and parameter sizes, and comprehensive evaluation metrics. Our findings highlight the significant influence of various prompt factors, show the performance of open-source LLMs compared to the commercial GPT-4 and the traditional Evosuite, and identify limitations in LLM-based unit test generation. We then derive a series of implications from our study to guide future research and practical use of LLM-based unit test generation.

In natural language processing, transformer-based large language models (LLMs) like GPT-x models developed by OpenAI have revolutionized the landscape. Despite their impressive capabilities, these models often encounter challenges when handling tasks that differ from their training data, resulting in compromised performance. To address this, few-shot learning has emerged as a valuable technique, allowing LLMs to adapt with minimal task-specific data. One innovative strategy, known as Chain-of-Thought Prompting (CoT), has been introduced to guide LLMs in revealing cognitive processes during multi-step reasoning. In this paper, we propose Code Chain-of-Thought~(CodeCoT), which consists of two components: the Vanilla CodeCoT and the Self-exam CodeCoT. The latter incorporates self-examination, empowering the model to iteratively generate code, formulate test cases, and refine its outputs. Specifically, the process entails the generation of test examples by the model corresponding to the code it is tasked to implement. If it fails on the test examples, then it regenerates the code based on the erroneous code and associated error types. Through comprehensive experiments, we observed that both techniques significantly enhance code generation accuracy across various LLM variants. Our evaluation results reveal that CodeCoT improves the code generation effectiveness, including an unprecedented pass@1 accuracy of 79.27\% using the Self-exam CodeCoT approach on the gpt-3.5-turbo-0613 model in the HumanEval dataset.

Despite their sophisticated capabilities, large language models (LLMs) encounter a major hurdle in effective assessment. This paper first revisits the prevalent evaluation method-multiple choice question answering (MCQA), which allows for straightforward accuracy measurement. Through a comprehensive evaluation of 24 models across 11 benchmarks, we highlight several potential drawbacks of MCQA, for instance, the inconsistency between the MCQA evaluation and the generation of open-ended responses in practical scenarios. In response, we introduce an RWQ-Elo rating system, engaging 24 LLMs such as GPT-4, GPT-3.5, Google-Gemini-Pro and LLaMA-1/-2, in a two-player competitive format, with GPT-4 serving as the judge. Each LLM receives an Elo rating thereafter. This system is designed to mirror real-world usage, and for this purpose, we have compiled a new benchmark called ``Real-world questions'' (RWQ), comprising 20,772 authentic user inquiries. Additionally, we thoroughly analyze the characteristics of our system and compare it with prior leaderboards like AlpacaEval and MT-Bench. Our analysis reveals the stability of our RWQ-Elo system, the feasibility of registering new models, and its potential to reshape LLM leaderboards.

In this paper, we investigate the effectiveness of state-of-the-art LLM, i.e., GPT-4, with three different prompting engineering techniques (i.e., basic prompting, in-context learning, and task-specific prompting) against 18 fine-tuned LLMs on three typical ASE tasks, i.e., code generation, code summarization, and code translation. Our quantitative analysis of these prompting strategies suggests that prompt engineering GPT-4 cannot necessarily and significantly outperform fine-tuning smaller/older LLMs in all three tasks. For comment generation, GPT-4 with the best prompting strategy (i.e., task-specific prompt) had outperformed the first-ranked fine-tuned model by 8.33% points on average in BLEU. However, for code generation, the first-ranked fine-tuned model outperforms GPT-4 with best prompting by 16.61% and 28.3% points, on average in BLEU. For code translation, GPT-4 and fine-tuned baselines tie as they outperform each other on different translation tasks. To explore the impact of different prompting strategies, we conducted a user study with 27 graduate students and 10 industry practitioners. From our qualitative analysis, we find that the GPT-4 with conversational prompts (i.e., when a human provides feedback and instructions back and forth with a model to achieve best results) showed drastic improvement compared to GPT-4 with automatic prompting strategies. Moreover, we observe that participants tend to request improvements, add more context, or give specific instructions as conversational prompts, which goes beyond typical and generic prompting strategies. Our study suggests that, at its current state, GPT-4 with conversational prompting has great potential for ASE tasks, but fully automated prompt engineering with no human in the loop requires more study and improvement.

Large language models (LLMs) have significantly advanced the field of natural language processing, with GPT models at the forefront. While their remarkable performance spans a range of tasks, adapting LLMs for real-world business scenarios still poses challenges warranting further investigation. This paper presents an empirical analysis aimed at bridging the gap in adapting LLMs to practical use cases. To do that, we select the question answering (QA) task of insurance as a case study due to its challenge of reasoning. Based on the task we design a new model relied on LLMs which are empowered by additional knowledge extracted from insurance policy rulebooks and DBpedia. The additional knowledge helps LLMs to understand new concepts of insurance for domain adaptation. Preliminary results on two QA datasets show that knowledge enhancement significantly improves the reasoning ability of GPT-3.5 (55.80% and 57.83% in terms of accuracy). The analysis also indicates that existing public knowledge bases, e.g., DBPedia is beneficial for knowledge enhancement. Our findings reveal that the inherent complexity of business scenarios often necessitates the incorporation of domain-specific knowledge and external resources for effective problem-solving.

Proof assistants like Lean have revolutionized mathematical proof verification, ensuring high accuracy and reliability. Although large language models (LLMs) show promise in mathematical reasoning, their advancement in formal theorem proving is hindered by a lack of training data. To address this issue, we introduce an approach to generate extensive Lean 4 proof data derived from high-school and undergraduate-level mathematical competition problems. This approach involves translating natural language problems into formal statements, filtering out low-quality statements, and generating proofs to create synthetic data. After fine-tuning the DeepSeekMath 7B model on this synthetic dataset, which comprises 8 million formal statements with proofs, our model achieved whole-proof generation accuracies of 46.3% with 64 samples and 52% cumulatively on the Lean 4 miniF2F test, surpassing the baseline GPT-4 at 23.0% with 64 samples and a tree search reinforcement learning method at 41.0%. Additionally, our model successfully proved 5 out of 148 problems in the Lean 4 Formalized International Mathematical Olympiad (FIMO) benchmark, while GPT-4 failed to prove any. These results demonstrate the potential of leveraging large-scale synthetic data to enhance theorem-proving capabilities in LLMs. Both the synthetic dataset and the model will be made available to facilitate further research in this promising field.

Recent advancements in LLM-based agents have led to significant progress in automatic software engineering, particularly in software maintenance and evolution. Despite these encouraging advances, current research faces two major challenges. First, SOTA performance primarily depends on closed-source models, which significantly limits the technology's accessibility, and potential for customization in diverse SE tasks. Second, these models are predominantly trained on static code data, lacking a deep understanding of the dynamic interactions, iterative problem-solving processes, and evolutionary characteristics inherent in software development. To address these challenges, our study adopts a software engineering perspective. We recognize that real-world software maintenance and evolution processes encompass not only static code data but also developers' thought processes, utilization of external tools, and the interaction between different functional personnel. Consequently, we introduce the Lingma SWE-GPT series, comprising Lingma SWE-GPT 7B and 72B. By learning from and simulating real-world code submission activities, Lingma SWE-GPT systematically incorporates the dynamic interactions and iterative problem-solving inherent in software development process, thereby achieving a more comprehensive understanding of software improvement processes. We conducted experimental evaluations using SWE-bench Verified benchmark. The results demonstrate that Lingma SWE-GPT 72B successfully resolves 30.20% of the GitHub issues, marking a significant improvement in automatic issue resolution (22.76% relative improvement compared to Llama 3.1 405B), approaching the performance of closed-source models (31.80\% issues of GPT-4o resolved). Notably, Lingma SWE-GPT 7B resolves 18.20% of the issues, highlighting the potential for applying smaller models to ASE tasks.

In light of recent breakthroughs in large language models (LLMs) that have revolutionized natural language processing (NLP), there is an urgent need for new benchmarks to keep pace with the fast development of LLMs. In this paper, we propose CFLUE, the Chinese Financial Language Understanding Evaluation benchmark, designed to assess the capability of LLMs across various dimensions. Specifically, CFLUE provides datasets tailored for both knowledge assessment and application assessment. In knowledge assessment, it consists of 38K+ multiple-choice questions with associated solution explanations. These questions serve dual purposes: answer prediction and question reasoning. In application assessment, CFLUE features 16K+ test instances across distinct groups of NLP tasks such as text classification, machine translation, relation extraction, reading comprehension, and text generation. Upon CFLUE, we conduct a thorough evaluation of representative LLMs. The results reveal that only GPT-4 and GPT-4-turbo achieve an accuracy exceeding 60\% in answer prediction for knowledge assessment, suggesting that there is still substantial room for improvement in current LLMs. In application assessment, although GPT-4 and GPT-4-turbo are the top two performers, their considerable advantage over lightweight LLMs is noticeably diminished. The datasets and scripts associated with CFLUE are openly accessible at https://github.com/aliyun/cflue.

In current NLP research, large-scale language models and their abilities are widely being discussed. Some recent works have also found notable failures of these models. Often these failure examples involve complex reasoning abilities. This work focuses on a simple commonsense ability, reasoning about when an action (or its effect) is feasible. To this end, we introduce FeasibilityQA, a question-answering dataset involving binary classification (BCQ) and multi-choice multi-correct questions (MCQ) that test understanding of feasibility. We show that even state-of-the-art models such as GPT-3, GPT-2, and T5 struggle to answer the feasibility questions correctly. Specifically, on MCQ and BCQ questions, GPT-3 achieves an accuracy of just (19%, 62%) and (25%, 64%) in zero-shot and few-shot settings, respectively. We also evaluate models by providing relevant knowledge statements required to answer the question. We find that the additional knowledge leads to a 7% gain in performance, but the overall performance still remains low. These results make one wonder how much commonsense knowledge about action feasibility is encoded in state-of-the-art models and how well they can reason about it.

Multimodal large language models acquire their instruction-following capabilities through a two-stage training process: pre-training on image-text pairs and fine-tuning on supervised vision-language instruction data. Recent studies have shown that large language models can achieve satisfactory results even with a limited amount of high-quality instruction-following data. In this paper, we introduce InstructionGPT-4, which is fine-tuned on a small dataset comprising only 200 examples, amounting to approximately 6% of the instruction-following data used in the alignment dataset for MiniGPT-4. We first propose several metrics to access the quality of multimodal instruction data. Based on these metrics, we present a simple and effective data selector to automatically identify and filter low-quality vision-language data. By employing this method, InstructionGPT-4 outperforms the original MiniGPT-4 on various evaluations (e.g., visual question answering, GPT-4 preference). Overall, our findings demonstrate that less but high-quality instruction tuning data is efficient to enable multimodal large language models to generate better output.

The rapid evolution of artificial intelligence (AI), especially in the domain of Large Language Models (LLMs) and generative AI, has opened new avenues for application across various fields, yet its role in business education remains underexplored. This study introduces the first benchmark to assess the performance of seven major LLMs, OpenAI's models (GPT-3.5 Turbo, GPT-4, and GPT-4 Turbo), Google's models (PaLM 2, Gemini 1.0 Pro), and Anthropic's models (Claude 2 and Claude 2.1), on the GMAT, which is a key exam in the admission process for graduate business programs. Our analysis shows that most LLMs outperform human candidates, with GPT-4 Turbo not only outperforming the other models but also surpassing the average scores of graduate students at top business schools. Through a case study, this research examines GPT-4 Turbo's ability to explain answers, evaluate responses, identify errors, tailor instructions, and generate alternative scenarios. The latest LLM versions, GPT-4 Turbo, Claude 2.1, and Gemini 1.0 Pro, show marked improvements in reasoning tasks compared to their predecessors, underscoring their potential for complex problem-solving. While AI's promise in education, assessment, and tutoring is clear, challenges remain. Our study not only sheds light on LLMs' academic potential but also emphasizes the need for careful development and application of AI in education. As AI technology advances, it is imperative to establish frameworks and protocols for AI interaction, verify the accuracy of AI-generated content, ensure worldwide access for diverse learners, and create an educational environment where AI supports human expertise. This research sets the stage for further exploration into the responsible use of AI to enrich educational experiences and improve exam preparation and assessment methods.

Linear programming (LP) problems are pervasive in real-life applications. However, despite their apparent simplicity, an untrained user may find it difficult to determine the linear model of their specific problem. We envisage the creation of a goal-oriented conversational agent that will engage in conversation with the user to elicit all information required so that a subsequent agent can generate the linear model. In this paper, we present an approach for the generation of sample dialogues that can be used to develop and train such a conversational agent. Using prompt engineering, we develop two agents that "talk" to each other, one acting as the conversational agent, and the other acting as the user. Using a set of text descriptions of linear problems from NL4Opt available to the user only, the agent and the user engage in conversation until the agent has retrieved all key information from the original problem description. We also propose an extrinsic evaluation of the dialogues by assessing how well the summaries generated by the dialogues match the original problem descriptions. We conduct human and automatic evaluations, including an evaluation approach that uses GPT-4 to mimic the human evaluation metrics. The evaluation results show an overall good quality of the dialogues, though research is still needed to improve the quality of the GPT-4 evaluation metrics. The resulting dialogues, including the human annotations of a subset, are available to the research community. The conversational agent used for the generation of the dialogues can be used as a baseline.

In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i.e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task. Our experiments thoroughly assess GPT-4V's proficiency in answering questions paired with images using both pathology and radiology datasets from 11 modalities (e.g. Microscopy, Dermoscopy, X-ray, CT, etc.) and fifteen objects of interests (brain, liver, lung, etc.). Our datasets encompass a comprehensive range of medical inquiries, including sixteen distinct question types. Throughout our evaluations, we devised textual prompts for GPT-4V, directing it to synergize visual and textual information. The experiments with accuracy score conclude that the current version of GPT-4V is not recommended for real-world diagnostics due to its unreliable and suboptimal accuracy in responding to diagnostic medical questions. In addition, we delineate seven unique facets of GPT-4V's behavior in medical VQA, highlighting its constraints within this complex arena. The complete details of our evaluation cases are accessible at https://github.com/ZhilingYan/GPT4V-Medical-Report.

We introduce Complex-Edit, a comprehensive benchmark designed to systematically evaluate instruction-based image editing models across instructions of varying complexity. To develop this benchmark, we harness GPT-4o to automatically collect a diverse set of editing instructions at scale. Our approach follows a well-structured ``Chain-of-Edit'' pipeline: we first generate individual atomic editing tasks independently and then integrate them to form cohesive, complex instructions. Additionally, we introduce a suite of metrics to assess various aspects of editing performance, along with a VLM-based auto-evaluation pipeline that supports large-scale assessments. Our benchmark yields several notable insights: 1) Open-source models significantly underperform relative to proprietary, closed-source models, with the performance gap widening as instruction complexity increases; 2) Increased instructional complexity primarily impairs the models' ability to retain key elements from the input images and to preserve the overall aesthetic quality; 3) Decomposing a complex instruction into a sequence of atomic steps, executed in a step-by-step manner, substantially degrades performance across multiple metrics; 4) A straightforward Best-of-N selection strategy improves results for both direct editing and the step-by-step sequential approach; and 5) We observe a ``curse of synthetic data'': when synthetic data is involved in model training, the edited images from such models tend to appear increasingly synthetic as the complexity of the editing instructions rises -- a phenomenon that intriguingly also manifests in the latest GPT-4o outputs.

Code generation is to automatically generate source code conforming to a given programming specification, which has received extensive attention especially with the development of large language models (LLMs). Due to the inherent difficulty of code generation, the code generated by LLMs may be also not aligned with the specification. To improve the perfor mance of LLMs in code generation, some Chain of Thought (CoT) techniques have been proposed to guide LLMs for programming understanding before code generation. However, they are still hard to figure out complicated programming logic according to the (concise) specification, leadingto unsatisfactory code generation performance. In this work, we propose the first test-case-driven CoT technique, called TCoT, to further enhance the ability of LLMs in code generation. It understands the programming specification from the novel perspective of test cases, which is aligned with human practice by using examples to understand complicated problems. Due to the existence of the expected output specified in a test case, TCoT can instantly check the correctness of the programming understanding and then refine it to be as correct as possible before code generation. In this way, it is more likely to generate correct code. Our evaluation on 6 datasets and 14 baselines demonstrates the effectiveness of TCoT. For example, TCoT improves ChatGPT by 13.93%~69.44% in terms of Pass@1 (measuring the ratio of programming problems for which the generated code passes all test cases), and outperforms the existing CoT technique with the improvement of 12.14%~53.72% in terms of Pass@1.

Financial analysis is an important tool for evaluating company performance. Practitioners work to answer financial questions to make profitable investment decisions, and use advanced quantitative analyses to do so. As a result, Financial Question Answering (QA) is a question answering task that requires deep reasoning about numbers. Furthermore, it is unknown how well pre-trained language models can reason in the financial domain. The current state-of-the-art requires a retriever to collect relevant facts about the financial question from the text and a generator to produce a valid financial program and a final answer. However, recently large language models like GPT-3 have achieved state-of-the-art performance on wide variety of tasks with just a few shot examples. We run several experiments with GPT-3 and find that a separate retrieval model and logic engine continue to be essential components to achieving SOTA performance in this task, particularly due to the precise nature of financial questions and the complex information stored in financial documents. With this understanding, our refined prompt-engineering approach on GPT-3 achieves near SOTA accuracy without any fine-tuning.

We present WebGLM, a web-enhanced question-answering system based on the General Language Model (GLM). Its goal is to augment a pre-trained large language model (LLM) with web search and retrieval capabilities while being efficient for real-world deployments. To achieve this, we develop WebGLM with strategies for the LLM-augmented retriever, bootstrapped generator, and human preference-aware scorer. Specifically, we identify and address the limitations of WebGPT (OpenAI), through which WebGLM is enabled with accuracy, efficiency, and cost-effectiveness advantages. In addition, we propose systematic criteria for evaluating web-enhanced QA systems. We conduct multi-dimensional human evaluation and quantitative ablation studies, which suggest the outperformance of the proposed WebGLM designs over existing systems. WebGLM with the 10-billion-parameter GLM (10B) is shown to perform better than the similar-sized WebGPT (13B) and even comparably to WebGPT (175B) in human evaluation. The code, demo, and data are at https://github.com/THUDM/WebGLM.

Competition-level code generation tasks pose significant challenges for current state-of-the-art large language models (LLMs). For example, on the LiveCodeBench-Hard dataset, models such as O1-Mini and O1-Preview achieve pass@1 rates of only 0.366 and 0.143, respectively. While tree search techniques have proven effective in domains like mathematics and general coding, their potential in competition-level code generation remains under-explored. In this work, we propose a novel token-level tree search method specifically designed for code generation. Leveraging Qwen2.5-Coder-32B-Instruct, our approach achieves a pass rate of 0.305 on LiveCodeBench-Hard, surpassing the pass@100 performance of GPT4o-0513 (0.245). Furthermore, by integrating Chain-of-Thought (CoT) prompting, we improve our method's performance to 0.351, approaching O1-Mini's pass@1 rate. To ensure reproducibility, we report the average number of generations required per problem by our tree search method on the test set. Our findings underscore the potential of tree search to significantly enhance performance on competition-level code generation tasks. This opens up new possibilities for large-scale synthesis of challenging code problems supervised fine-tuning (SFT) data, advancing competition-level code generation tasks.

Large language models (LLMs) are increasingly used as personal agents, accessing sensitive user data such as calendars, emails, and medical records. Users currently face a trade-off: They can send private records, many of which are stored in remote databases, to powerful but untrusted LLM providers, increasing their exposure risk. Alternatively, they can run less powerful models locally on trusted devices. We bridge this gap. Our Socratic Chain-of-Thought Reasoning first sends a generic, non-private user query to a powerful, untrusted LLM, which generates a Chain-of-Thought (CoT) prompt and detailed sub-queries without accessing user data. Next, we embed these sub-queries and perform encrypted sub-second semantic search using our Homomorphically Encrypted Vector Database across one million entries of a single user's private data. This represents a realistic scale of personal documents, emails, and records accumulated over years of digital activity. Finally, we feed the CoT prompt and the decrypted records to a local language model and generate the final response. On the LoCoMo long-context QA benchmark, our hybrid framework, combining GPT-4o with a local Llama-3.2-1B model, outperforms using GPT-4o alone by up to 7.1 percentage points. This demonstrates a first step toward systems where tasks are decomposed and split between untrusted strong LLMs and weak local ones, preserving user privacy.

Large language models are redefining software engineering by implementing AI-powered techniques throughout the whole software development process, including requirement gathering, software architecture, code generation, testing, and deployment. However, it is still difficult to develop a cohesive platform that consistently produces the best outcomes across all stages. The objective of this study is to develop a unified platform that utilizes multiple artificial intelligence agents to automate the process of transforming user requirements into well-organized deliverables. These deliverables include user stories, prioritization, and UML sequence diagrams, along with the modular approach to APIs, unit tests, and end-to-end tests. Additionally, the platform will organize tasks, perform security and compliance, and suggest design patterns and improvements for non-functional requirements. We allow users to control and manage each phase according to their preferences. In addition, the platform provides security and compliance checks following European standards and proposes design optimizations. We use multiple models, such as GPT-3.5, GPT-4, and Llama3 to enable to generation of modular code as per user choice. The research also highlights the limitations and future research discussions to overall improve the software development life cycle. The source code for our uniform platform is hosted on GitHub, enabling additional experimentation and supporting both research and practical uses. \end

Software testing is a critical aspect of software development, yet generating test cases remains a routine task for engineers. This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases under specific conditions. Spanning from simple assertion completions to writing test cases that cover specific code blocks across multiple files, these tasks are based on 12 python repositories, analyzing 845 problems with context lengths ranging from 4k to 128k tokens. Utilizing code testing frameworks, we propose a method to construct retrieval contexts using coverage information. While models exhibit comparable performance with short contexts, notable differences emerge with 16k contexts. Notably, models like GPT-4o and Claude 3.5 can effectively leverage relevant snippets; however, all models score below 35\% on the complex Task III, even with the oracle context provided, underscoring the benchmark's significance and the potential for model improvement. The benchmark is containerized for code execution across tasks, and we will release the code, data, and construction methodologies.

Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning depends on the availability of high-quality instruction data. Owing to the exorbitant cost and substandard quality of human annotation, recent works have been deeply engaged in the exploration of the utilization of powerful closed-source models to generate instruction data automatically. However, these methods carry potential risks arising from the usage requirements of powerful closed-source models, which strictly forbid the utilization of their outputs to develop machine learning models. To deal with this problem, in this work, we explore alternative approaches to generate high-quality instruction data that do not rely on closed-source models. Our exploration includes an investigation of various existing instruction generation methods, culminating in the integration of the most efficient variant with two novel strategies to enhance the quality further. Evaluation results from two benchmarks and the GPT-4 model demonstrate the effectiveness of our generated instruction data, which can outperform Alpaca, a method reliant on closed-source models. We hope that more progress can be achieved in generating high-quality instruction data without using closed-source models.

We study the code generation behavior of instruction-tuned models built on top of code pre-trained language models when they could access an auxiliary function to implement a function. We design several ways to provide auxiliary functions to the models by adding them to the query or providing a response prefix to incorporate the ability to utilize auxiliary functions with the instruction-following capability. Our experimental results show the effectiveness of combining the base models' auxiliary function utilization ability with the instruction following ability. In particular, the performance of adopting our approaches with the open-sourced language models surpasses that of the recent powerful proprietary language models, i.e., gpt-4o.

Collecting large amounts of real-world interaction data to train general robotic policies is often prohibitively expensive, thus motivating the use of simulation data. However, existing methods for data generation have generally focused on scene-level diversity (e.g., object instances and poses) rather than task-level diversity, due to the human effort required to come up with and verify novel tasks. This has made it challenging for policies trained on simulation data to demonstrate significant task-level generalization. In this paper, we propose to automatically generate rich simulation environments and expert demonstrations by exploiting a large language models' (LLM) grounding and coding ability. Our approach, dubbed GenSim, has two modes: goal-directed generation, wherein a target task is given to the LLM and the LLM proposes a task curriculum to solve the target task, and exploratory generation, wherein the LLM bootstraps from previous tasks and iteratively proposes novel tasks that would be helpful in solving more complex tasks. We use GPT4 to expand the existing benchmark by ten times to over 100 tasks, on which we conduct supervised finetuning and evaluate several LLMs including finetuned GPTs and Code Llama on code generation for robotic simulation tasks. Furthermore, we observe that LLMs-generated simulation programs can enhance task-level generalization significantly when used for multitask policy training. We further find that with minimal sim-to-real adaptation, the multitask policies pretrained on GPT4-generated simulation tasks exhibit stronger transfer to unseen long-horizon tasks in the real world and outperform baselines by 25%. See the project website (https://liruiw.github.io/gensim) for code, demos, and videos.

This paper presents Safurai-001, a new Large Language Model (LLM) with significant potential in the domain of coding assistance. Driven by recent advancements in coding LLMs, Safurai-001 competes in performance with the latest models like WizardCoder [Xu et al., 2023], PanguCoder [Shen et al., 2023] and Phi-1 [Gunasekar et al., 2023] but aims to deliver a more conversational interaction. By capitalizing on the progress in data engineering (including latest techniques of data transformation and prompt engineering) and instruction tuning, this new model promises to stand toe-to-toe with recent closed and open source developments. Recognizing the need for an efficacious evaluation metric for coding LLMs, this paper also introduces GPT4-based MultiParameters, an evaluation benchmark that harnesses varied parameters to present a comprehensive insight into the models functioning and performance. Our assessment shows that Safurai-001 can outperform GPT-3.5 by 1.58% and WizardCoder by 18.78% in the Code Readability parameter and more.

We introduce CRPE (Code Reasoning Process Enhancer), an innovative three-stage framework for data synthesis and model training that advances the development of sophisticated code reasoning capabilities in large language models (LLMs). Building upon existing system-1 models, CRPE addresses the fundamental challenge of enhancing LLMs' analytical and logical processing in code generation tasks. Our framework presents a methodologically rigorous yet implementable approach to cultivating advanced code reasoning abilities in language models. Through the implementation of CRPE, we successfully develop an enhanced COT-Coder that demonstrates marked improvements in code generation tasks. Evaluation results on LiveCodeBench (20240701-20240901) demonstrate that our COT-Coder-7B-StepDPO, derived from Qwen2.5-Coder-7B-Base, with a pass@1 accuracy of 21.88, exceeds all models with similar or even larger sizes. Furthermore, our COT-Coder-32B-StepDPO, based on Qwen2.5-Coder-32B-Base, exhibits superior performance with a pass@1 accuracy of 35.08, outperforming GPT4O on the benchmark. Overall, CRPE represents a comprehensive, open-source method that encompasses the complete pipeline from instruction data acquisition through expert code reasoning data synthesis, culminating in an autonomous reasoning enhancement mechanism.

Autonomous agents that address day-to-day digital tasks (e.g., ordering groceries for a household), must not only operate multiple apps (e.g., notes, messaging, shopping app) via APIs, but also generate rich code with complex control flow in an iterative manner based on their interaction with the environment. However, existing benchmarks for tool use are inadequate, as they only cover tasks that require a simple sequence of API calls. To remedy this gap, we built AppWorld Engine, a high-quality execution environment (60K lines of code) of 9 day-to-day apps operable via 457 APIs and populated with realistic digital activities simulating the lives of ~100 fictitious users. We then created AppWorld Benchmark (40K lines of code), a suite of 750 natural, diverse, and challenging autonomous agent tasks requiring rich and interactive code generation. It supports robust programmatic evaluation with state-based unit tests, allowing for different ways of completing a task while also checking for unexpected changes, i.e., collateral damage. The state-of-the-art LLM, GPT-4o, solves only ~49% of our 'normal' tasks and ~30% of 'challenge' tasks, while other models solve at least 16% fewer. This highlights the benchmark's difficulty and AppWorld's potential to push the frontiers of interactive coding agents. The project website is available at https://appworld.dev/.

Recent advances in Large Language Models (LLMs) have sparked growing interest in applying them to Electronic Design Automation (EDA) tasks, particularly Register Transfer Level (RTL) code generation. While several RTL datasets have been introduced, most focus on syntactic validity rather than functional validation with tests, leading to training examples that compile but may not implement the intended behavior. We present VERICODER, a model for RTL code generation fine-tuned on a dataset validated for functional correctness. This fine-tuning dataset is constructed using a novel methodology that combines unit test generation with feedback-directed refinement. Given a natural language specification and an initial RTL design, we prompt a teacher model (GPT-4o-mini) to generate unit tests and iteratively revise the RTL design based on its simulation results using the generated tests. If necessary, the teacher model also updates the tests to ensure they comply with the natural language specification. As a result of this process, every example in our dataset is functionally validated, consisting of a natural language description, an RTL implementation, and passing tests. Fine-tuned on this dataset of over 125,000 examples, VERICODER achieves state-of-the-art metrics in functional correctness on VerilogEval and RTLLM, with relative gains of up to 71.7% and 27.4% respectively. An ablation study further shows that models trained on our functionally validated dataset outperform those trained on functionally non-validated datasets, underscoring the importance of high-quality datasets in RTL code generation.

A common way of assessing language learners' mastery of vocabulary is via multiple-choice cloze (i.e., fill-in-the-blank) questions. But the creation of test items can be laborious for individual teachers or in large-scale language programs. In this paper, we evaluate a new method for automatically generating these types of questions using large language models (LLM). The VocaTT (vocabulary teaching and training) engine is written in Python and comprises three basic steps: pre-processing target word lists, generating sentences and candidate word options using GPT, and finally selecting suitable word options. To test the efficiency of this system, 60 questions were generated targeting academic words. The generated items were reviewed by expert reviewers who judged the well-formedness of the sentences and word options, adding comments to items judged not well-formed. Results showed a 75% rate of well-formedness for sentences and 66.85% rate for suitable word options. This is a marked improvement over the generator used earlier in our research which did not take advantage of GPT's capabilities. Post-hoc qualitative analysis reveals several points for improvement in future work including cross-referencing part-of-speech tagging, better sentence validation, and improving GPT prompts.

In this work, we conduct an experiment using state-of-the-art LLMs to translate MiniF2F into Rocq. The translation task focuses on generating a Rocq theorem based on three sources: a natural language description, the Lean formalization, and the Isabelle formalization. We conducted our experiment in 3 stages of increasing complexity, from basic one-shot prompting to multi-turn conversations that incorporate feedback from unsuccessful attempts. At each stage, we perform multiple rounds of translation using increasingly advanced models: GPT-4o mini, Claude 3.5 Sonnet, o1 mini, and o1. We successfully translated 478 out of 488 theorems. The dataset is opensource: https://github.com/LLM4Rocq/miniF2F-rocq.

How to evaluate Large Language Models (LLMs) in code generation is an open question. Existing benchmarks demonstrate poor alignment with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. This paper proposes a new benchmark - EvoCodeBench to address the preceding problems, which has three primary advances. (1) EvoCodeBench aligns with real-world repositories in multiple dimensions, e.g., code distributions and dependency distributions. (2) EvoCodeBench offers comprehensive annotations (e.g., requirements, reference code, and reference dependencies), and robust evaluation metrics (e.g., Pass@k and Recall@k). (3) EvoCodeBench is an evolving benchmark to avoid data leakage. We build an automatic pipeline to update EvoCodeBench from the latest repositories. We release the first version - EvoCodeBench-2403, containing 275 samples from 25 real-world repositories. Based on EvoCodeBench, we propose repository-level code generation and evaluate 10 popular LLMs (e.g., gpt-4, gpt-3.5, DeepSeek Coder, StarCoder 2, CodeLLaMa, Gemma, and Qwen 1.5). Our experiments reveal the coding abilities of these LLMs in real-world repositories. For example, the highest Pass@1 of gpt-4 only is 20.73% in our experiments. We also analyze failed cases and summarize the shortcomings of existing LLMs in EvoCodeBench. We release EvoCodeBench, all prompts, and LLMs' completions for further community analysis.

The advancement of natural language processing (NLP) has been significantly boosted by the development of transformer-based large language models (LLMs). These models have revolutionized NLP tasks, particularly in code generation, aiding developers in creating software with enhanced efficiency. Despite their advancements, challenges in balancing code snippet generation with effective test case generation and execution persist. To address these issues, this paper introduces Multi-Agent Assistant Code Generation (AgentCoder), a novel solution comprising a multi-agent framework with specialized agents: the programmer agent, the test designer agent, and the test executor agent. During the coding procedure, the programmer agent will focus on the code generation and refinement based on the test executor agent's feedback. The test designer agent will generate test cases for the generated code, and the test executor agent will run the code with the test cases and write the feedback to the programmer. This collaborative system ensures robust code generation, surpassing the limitations of single-agent models and traditional methodologies. Our extensive experiments on 9 code generation models and 12 enhancement approaches showcase AgentCoder's superior performance over existing code generation models and prompt engineering techniques across various benchmarks. For example, AgentCoder achieves 77.4% and 89.1% pass@1 in HumanEval-ET and MBPP-ET with GPT-3.5, while SOTA baselines obtain only 69.5% and 63.0%.

Synthesizing inductive loop invariants is fundamental to automating program verification. In this work, we observe that Large Language Models (such as gpt-3.5 or gpt-4) are capable of synthesizing loop invariants for a class of programs in a 0-shot setting, yet require several samples to generate the correct invariants. This can lead to a large number of calls to a program verifier to establish an invariant. To address this issue, we propose a {\it re-ranking} approach for the generated results of LLMs. We have designed a ranker that can distinguish between correct inductive invariants and incorrect attempts based on the problem definition. The ranker is optimized as a contrastive ranker. Experimental results demonstrate that this re-ranking mechanism significantly improves the ranking of correct invariants among the generated candidates, leading to a notable reduction in the number of calls to a verifier.

We introduce HackSynth, a novel Large Language Model (LLM)-based agent capable of autonomous penetration testing. HackSynth's dual-module architecture includes a Planner and a Summarizer, which enable it to generate commands and process feedback iteratively. To benchmark HackSynth, we propose two new Capture The Flag (CTF)-based benchmark sets utilizing the popular platforms PicoCTF and OverTheWire. These benchmarks include two hundred challenges across diverse domains and difficulties, providing a standardized framework for evaluating LLM-based penetration testing agents. Based on these benchmarks, extensive experiments are presented, analyzing the core parameters of HackSynth, including creativity (temperature and top-p) and token utilization. Multiple open source and proprietary LLMs were used to measure the agent's capabilities. The experiments show that the agent performed best with the GPT-4o model, better than what the GPT-4o's system card suggests. We also discuss the safety and predictability of HackSynth's actions. Our findings indicate the potential of LLM-based agents in advancing autonomous penetration testing and the importance of robust safeguards. HackSynth and the benchmarks are publicly available to foster research on autonomous cybersecurity solutions.

Existing benchmarks fail to capture a crucial aspect of intelligence: physical reasoning, the integrated ability to combine domain knowledge, symbolic reasoning, and understanding of real-world constraints. To address this gap, we introduce PhyX: the first large-scale benchmark designed to assess models capacity for physics-grounded reasoning in visual scenarios. PhyX includes 3K meticulously curated multimodal questions spanning 6 reasoning types across 25 sub-domains and 6 core physics domains: thermodynamics, electromagnetism, mechanics, modern physics, optics, and wave\&acoustics. In our comprehensive evaluation, even state-of-the-art models struggle significantly with physical reasoning. GPT-4o, Claude3.7-Sonnet, and GPT-o4-mini achieve only 32.5\%, 42.2\%, and 45.8\% accuracy respectively-performance gaps exceeding 29\% compared to human experts. Our analysis exposes critical limitations in current models: over-reliance on memorized disciplinary knowledge, excessive dependence on mathematical formulations, and surface-level visual pattern matching rather than genuine physical understanding. We provide in-depth analysis through fine-grained statistics, detailed case studies, and multiple evaluation paradigms to thoroughly examine physical reasoning capabilities. To ensure reproducibility, we implement a compatible evaluation protocol based on widely-used toolkits such as VLMEvalKit, enabling one-click evaluation.

Commit messages are crucial to software development, allowing developers to track changes and collaborate effectively. Despite their utility, most commit messages lack important information since writing high-quality commit messages is tedious and time-consuming. The active research on commit message generation (CMG) has not yet led to wide adoption in practice. We argue that if we could shift the focus from commit message generation to commit message completion and use previous commit history as additional context, we could significantly improve the quality and the personal nature of the resulting commit messages. In this paper, we propose and evaluate both of these novel ideas. Since the existing datasets lack historical data, we collect and share a novel dataset called CommitChronicle, containing 10.7M commits across 20 programming languages. We use this dataset to evaluate the completion setting and the usefulness of the historical context for state-of-the-art CMG models and GPT-3.5-turbo. Our results show that in some contexts, commit message completion shows better results than generation, and that while in general GPT-3.5-turbo performs worse, it shows potential for long and detailed messages. As for the history, the results show that historical information improves the performance of CMG models in the generation task, and the performance of GPT-3.5-turbo in both generation and completion.

The widespread adoption of REST APIs, coupled with their growing complexity and size, has led to the need for automated REST API testing tools. Current testing tools focus on the structured data in REST API specifications but often neglect valuable insights available in unstructured natural-language descriptions in the specifications, which leads to suboptimal test coverage. Recently, to address this gap, researchers have developed techniques that extract rules from these human-readable descriptions and query knowledge bases to derive meaningful input values. However, these techniques are limited in the types of rules they can extract and can produce inaccurate results. This paper presents RESTGPT, an innovative approach that leverages the power and intrinsic context-awareness of Large Language Models (LLMs) to improve REST API testing. RESTGPT takes as input an API specification, extracts machine-interpretable rules, and generates example parameter values from natural-language descriptions in the specification. It then augments the original specification with these rules and values. Our preliminary evaluation suggests that RESTGPT outperforms existing techniques in both rule extraction and value generation. Given these encouraging results, we outline future research directions for leveraging LLMs more broadly for improving REST API testing.

Verifiers play a crucial role in large language model (LLM) reasoning, needed by post-training techniques such as reinforcement learning. However, reliable verifiers are hard to get for difficult coding problems, because a well-disguised wrong solution may only be detected by carefully human-written edge cases that are difficult to synthesize. To address this issue, we propose HARDTESTGEN, a pipeline for high-quality test synthesis using LLMs. With this pipeline, we curate a comprehensive competitive programming dataset HARDTESTS with 47k problems and synthetic high-quality tests. Compared with existing tests, HARDTESTGEN tests demonstrate precision that is 11.3 percentage points higher and recall that is 17.5 percentage points higher when evaluating LLM-generated code. For harder problems, the improvement in precision can be as large as 40 points. HARDTESTS also proves to be more effective for model training, measured by downstream code generation performance. We will open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.

There is growing interest in systems that generate captions for scientific figures. However, assessing these systems output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic evaluation depends on often low-quality author-written captions. This paper investigates using large language models (LLMs) as a cost-effective, reference-free method for evaluating figure captions. We first constructed SCICAP-EVAL, a human evaluation dataset that contains human judgments for 3,600 scientific figure captions, both original and machine-made, for 600 arXiv figures. We then prompted LLMs like GPT-4 and GPT-3 to score (1-6) each caption based on its potential to aid reader understanding, given relevant context such as figure-mentioning paragraphs. Results show that GPT-4, used as a zero-shot evaluator, outperformed all other models and even surpassed assessments made by Computer Science and Informatics undergraduates, achieving a Kendall correlation score of 0.401 with Ph.D. students rankings

Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs. However, concerns including transparency, controllability, and affordability strongly motivate the development of open-source LMs specialized in evaluations. On the other hand, existing open evaluator LMs exhibit critical shortcomings: 1) they issue scores that significantly diverge from those assigned by humans, and 2) they lack the flexibility to perform both direct assessment and pairwise ranking, the two most prevalent forms of assessment. Additionally, they do not possess the ability to evaluate based on custom evaluation criteria, focusing instead on general attributes like helpfulness and harmlessness. To address these issues, we introduce Prometheus 2, a more powerful evaluator LM than its predecessor that closely mirrors human and GPT-4 judgements. Moreover, it is capable of processing both direct assessment and pair-wise ranking formats grouped with a user-defined evaluation criteria. On four direct assessment benchmarks and four pairwise ranking benchmarks, Prometheus 2 scores the highest correlation and agreement with humans and proprietary LM judges among all tested open evaluator LMs. Our models, code, and data are all publicly available at https://github.com/prometheus-eval/prometheus-eval.

In this paper, we introduce Concise Chain-of-Thought (CCoT) prompting. We compared standard CoT and CCoT prompts to see how conciseness impacts response length and correct-answer accuracy. We evaluated this using GPT-3.5 and GPT-4 with a multiple-choice question-and-answer (MCQA) benchmark. CCoT reduced average response length by 48.70% for both GPT-3.5 and GPT-4 while having a negligible impact on problem-solving performance. However, on math problems, GPT-3.5 with CCoT incurs a performance penalty of 27.69%. Overall, CCoT leads to an average per-token cost reduction of 22.67%. These results have practical implications for AI systems engineers using LLMs to solve real-world problems with CoT prompt-engineering techniques. In addition, these results provide more general insight for AI researchers studying the emergent behavior of step-by-step reasoning in LLMs.

The Quantum Approximate Optimization Algorithm (QAOA) is a prominent variational algorithm used for solving combinatorial optimization problems such as the Max-Cut problem. A key challenge in QAOA lies in efficiently identifying suitable parameters (gamma, beta) that lead to high-quality solutions. In this paper, we propose a framework that combines Fully Informed Particle Swarm Optimization (FIPSO) with adaptive gradient correction using the Adam Optimizer to navigate the QAOA parameter space. This approach aims to avoid issues such as barren plateaus and convergence to local minima. The proposed algorithm is evaluated against two classes of graph instances, Erdos Renyi and Watts-Strogatz. Experimental results across multiple QAOA depths consistently demonstrate superior performance compared to random initialization, underscoring the effectiveness and robustness of the proposed optimization framework.

Unit testing is a commonly-used approach in software engineering to test the correctness and robustness of written code. Unit tests are tests designed to test small components of a codebase in isolation, such as an individual function or method. Although unit tests have historically been written by human programmers, recent advancements in AI, particularly LLMs, have shown corresponding advances in automatic unit test generation. In this study, we explore the effect of different prompts on the quality of unit tests generated by Code Interpreter, a GPT-4-based LLM, on Python functions provided by the Quixbugs dataset, and we focus on prompting due to the ease with which users can make use of our findings and observations. We find that the quality of the generated unit tests is not sensitive to changes in minor details in the prompts provided. However, we observe that Code Interpreter is often able to effectively identify and correct mistakes in code that it writes, suggesting that providing it runnable code to check the correctness of its outputs would be beneficial, even though we find that it is already often able to generate correctly-formatted unit tests. Our findings suggest that, when prompting models similar to Code Interpreter, it is important to include the basic information necessary to generate unit tests, but minor details are not as important.

For industrial control, developing high-performance controllers with few samples and low technical debt is appealing. Foundation models, possessing rich prior knowledge obtained from pre-training with Internet-scale corpus, have the potential to be a good controller with proper prompts. In this paper, we take HVAC (Heating, Ventilation, and Air Conditioning) building control as an example to examine the ability of GPT-4 (one of the first-tier foundation models) as the controller. To control HVAC, we wrap the task as a language game by providing text including a short description for the task, several selected demonstrations, and the current observation to GPT-4 on each step and execute the actions responded by GPT-4. We conduct series of experiments to answer the following questions: 1)~How well can GPT-4 control HVAC? 2)~How well can GPT-4 generalize to different scenarios for HVAC control? 3) How different parts of the text context affect the performance? In general, we found GPT-4 achieves the performance comparable to RL methods with few samples and low technical debt, indicating the potential of directly applying foundation models to industrial control tasks.

This study investigates the consistency of feedback ratings generated by OpenAI's GPT-4, a state-of-the-art artificial intelligence language model, across multiple iterations, time spans and stylistic variations. The model rated responses to tasks within the Higher Education (HE) subject domain of macroeconomics in terms of their content and style. Statistical analysis was conducted in order to learn more about the interrater reliability, consistency of the ratings across iterations and the correlation between ratings in terms of content and style. The results revealed a high interrater reliability with ICC scores ranging between 0.94 and 0.99 for different timespans, suggesting that GPT-4 is capable of generating consistent ratings across repetitions with a clear prompt. Style and content ratings show a high correlation of 0.87. When applying a non-adequate style the average content ratings remained constant, while style ratings decreased, which indicates that the large language model (LLM) effectively distinguishes between these two criteria during evaluation. The prompt used in this study is furthermore presented and explained. Further research is necessary to assess the robustness and reliability of AI models in various use cases.

Recently, there has been growing interest in using Large Language Models (LLMs) for scientific research. Numerous benchmarks have been proposed to evaluate the ability of LLMs for scientific research. However, current benchmarks are mostly based on pre-collected objective questions. This design suffers from data leakage problem and lacks the evaluation of subjective Q/A ability. In this paper, we propose SciEval, a comprehensive and multi-disciplinary evaluation benchmark to address these issues. Based on Bloom's taxonomy, SciEval covers four dimensions to systematically evaluate scientific research ability. In particular, we design a "dynamic" subset based on scientific principles to prevent evaluation from potential data leakage. Both objective and subjective questions are included in SciEval. These characteristics make SciEval a more effective benchmark for scientific research ability evaluation of LLMs. Comprehensive experiments on most advanced LLMs show that, although GPT-4 achieves SOTA performance compared to other LLMs, there is still substantial room for improvement, especially for dynamic questions. The data and codes are now publicly available.

Foundation Large Language Models (LLMs) such as GPT-4 represent a revolution in AI due to their real-world applications though natural language processing. However, they also pose many significant risks such as the presence of biased, private, or harmful text, and the unauthorized inclusion of copyrighted material. We introduce h2oGPT, a suite of open-source code repositories for the creation and use of Large Language Models (LLMs) based on Generative Pretrained Transformers (GPTs). The goal of this project is to create the world's best truly open-source alternative to closed-source GPTs. In collaboration with and as part of the incredible and unstoppable open-source community, we open-source several fine-tuned h2oGPT models from 7 to 40 Billion parameters, ready for commercial use under fully permissive Apache 2.0 licenses. Included in our release is 100% private document search using natural language. Open-source language models help boost AI development and make it more accessible and trustworthy. They lower entry hurdles, allowing people and groups to tailor these models to their needs. This openness increases innovation, transparency, and fairness. An open-source strategy is needed to share AI benefits fairly, and H2O.ai will continue to democratize AI and LLMs.

Despite recent progress made by large language models in code generation, they still struggle with programs that meet complex requirements. Recent work utilizes plan-and-solve decomposition to decrease the complexity and leverage self-tests to refine the generated program. Yet, planning deep-inside requirements in advance can be challenging, and the tests need to be accurate to accomplish self-improvement. To this end, we propose FunCoder, a code generation framework incorporating the divide-and-conquer strategy with functional consensus. Specifically, FunCoder recursively branches off sub-functions as smaller goals during code generation, represented by a tree hierarchy. These sub-functions are then composited to attain more complex objectives. Additionally, we designate functions via a consensus formed by identifying similarities in program behavior, mitigating error propagation. FunCoder outperforms state-of-the-art methods by +9.8% on average in HumanEval, MBPP, xCodeEval and MATH with GPT-3.5 and GPT-4. Moreover, our method demonstrates superiority on smaller models: With FunCoder, StableCode-3b surpasses GPT-3.5 by +18.6% and achieves 97.7% of GPT-4's performance on HumanEval. Further analysis reveals that our proposed dynamic function decomposition is capable of handling complex requirements, and the functional consensus prevails over self-testing in correctness evaluation.

Self-consistency (SC), leveraging multiple samples from LLMs, shows significant gains on various reasoning tasks but struggles with free-form generation due to the difficulty of aggregating answers. Its variants, UCS and USC, rely on sample selection or voting mechanisms to improve output quality. These methods, however, face limitations due to their inability to fully utilize the nuanced consensus knowledge present within multiple candidate samples, often resulting in suboptimal outputs. We propose Fine-Grained Self-Consistency (FSC) to addresses these limitations by extracting and integrating segment-level commonalities from candidate samples, enhancing the performance of LLMs both in open-ended and reasoning tasks. Based on this, we present two additional strategies: candidate filtering, which enhances overall quality by identifying highly similar candidate sets, and merging, which reduces input token requirements by combining similar samples. The effectiveness of FSC is demonstrated through extensive experiments on various tasks, including summarization, code generation, and mathematical reasoning, using GPT-3.5-turbo and GPT-4. The results indicate significant improvements over baseline methods, showcasing the potential of FSC to optimize output quality by effectively synthesizing fine-grained consensus knowledge from multiple samples.

Despite a widespread success in various applications, large language models (LLMs) often stumble when tackling basic physical reasoning or executing robotics tasks, due to a lack of direct experience with the physical nuances of the real world. To address these issues, we propose a Grounding Large language model with Imperfect world MOdel (GLIMO), which utilizes proxy world models such as simulators to collect and synthesize trining data. GLIMO incorporates an LLM agent-based data generator to automatically create high-quality and diverse instruction datasets. The generator includes an iterative self-refining module for temporally consistent experience sampling, a diverse set of question-answering instruction seeds, and a retrieval-augmented generation module for reflecting on prior experiences. Comprehensive experiments show that our approach improve the performance of strong open-source LLMs like LLaMA-3 with a performance boost of 2.04 times, 1.54 times, and 1.82 times across three different benchmarks, respectively. The performance is able to compete with or surpass their larger counterparts such as GPT-4.

Penetration testing, a crucial industrial practice for ensuring system security, has traditionally resisted automation due to the extensive expertise required by human professionals. Large Language Models (LLMs) have shown significant advancements in various domains, and their emergent abilities suggest their potential to revolutionize industries. In this research, we evaluate the performance of LLMs on real-world penetration testing tasks using a robust benchmark created from test machines with platforms. Our findings reveal that while LLMs demonstrate proficiency in specific sub-tasks within the penetration testing process, such as using testing tools, interpreting outputs, and proposing subsequent actions, they also encounter difficulties maintaining an integrated understanding of the overall testing scenario. In response to these insights, we introduce PentestGPT, an LLM-empowered automatic penetration testing tool that leverages the abundant domain knowledge inherent in LLMs. PentestGPT is meticulously designed with three self-interacting modules, each addressing individual sub-tasks of penetration testing, to mitigate the challenges related to context loss. Our evaluation shows that PentestGPT not only outperforms LLMs with a task-completion increase of 228.6\% compared to the \gptthree model among the benchmark targets but also proves effective in tackling real-world penetration testing challenges. Having been open-sourced on GitHub, PentestGPT has garnered over 4,700 stars and fostered active community engagement, attesting to its value and impact in both the academic and industrial spheres.

Recent reasoning LLMs (RLMs), especially those trained with verifier-based reinforcement learning, often perform worse with few-shot CoT than with direct answering. We revisit this paradox using high-quality reasoning traces from DeepSeek-R1 as demonstrations and find that adding more exemplars consistently degrades accuracy, even when demonstrations are optimal. A detailed analysis reveals two mechanisms behind this decline: (i) semantic misguidance, where high textual similarity leads the model to treat the target as the same as the exemplar and to copy intermediate steps verbatim; and (ii) strategy transfer failure, where the model struggles to extract useful reasoning strategies and apply them to target questions. Guided by these, we introduce Insight-to-Solve (I2S), a sequential test-time procedure that turns demonstrations into explicit, reusable insights and derives a target-specific reasoning trace; optionally, the reasoning is self-refined for coherence and correctness (I2S+). Extensive experiments on diverse benchmarks show that I2S and I2S+ consistently outperform both direct answering and test-time scaling baselines across open- and closed-source models. Even for GPT models, our method helps: on AIME'25, GPT-4.1 rises by +14.0%, and o1-mini improves by +2.7% on AIME and +1.7% on GPQA, indicating that in-context demonstrations can be harnessed effectively via insight-refine-solve framework.

This study evaluates the performance of ChatGPT variants, GPT-3.5 and GPT-4, both with and without prompt engineering, against solely student work and a mixed category containing both student and GPT-4 contributions in university-level physics coding assignments using the Python language. Comparing 50 student submissions to 50 AI-generated submissions across different categories, and marked blindly by three independent markers, we amassed n = 300 data points. Students averaged 91.9% (SE:0.4), surpassing the highest performing AI submission category, GPT-4 with prompt engineering, which scored 81.1% (SE:0.8) - a statistically significant difference (p = 2.482 times 10^{-10}). Prompt engineering significantly improved scores for both GPT-4 (p = 1.661 times 10^{-4}) and GPT-3.5 (p = 4.967 times 10^{-9}). Additionally, the blinded markers were tasked with guessing the authorship of the submissions on a four-point Likert scale from `Definitely AI' to `Definitely Human'. They accurately identified the authorship, with 92.1% of the work categorized as 'Definitely Human' being human-authored. Simplifying this to a binary `AI' or `Human' categorization resulted in an average accuracy rate of 85.3%. These findings suggest that while AI-generated work closely approaches the quality of university students' work, it often remains detectable by human evaluators.

Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is frequently used in the field of question generation (QG) and is one of the most accurate evaluation methods. It also serves as the standard for automatic metrics. However, there is a lack of unified evaluation criteria, which hampers the development of both QG technologies and automatic evaluation methods. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated questions and existing automatic metrics across 7 dimensions: fluency, clarity, conciseness, relevance, consistency, answerability, and answer consistency. We demonstrate the appropriateness of these dimensions by examining their correlations and distinctions. Analysis with QGEval reveals that 1) most QG models perform unsatisfactorily in terms of answerability and answer consistency, and 2) existing metrics fail to align well with human assessments when evaluating generated questions across the 7 dimensions. We expect this work to foster the development of both QG technologies and automatic metrics for QG.

Large language models (LLMs) have made significant progress in code generation tasks, but their performance in tackling programming problems with complex data structures and algorithms remains suboptimal. To address this issue, we propose an in-context learning approach that guides LLMs to debug by using a "print debugging" method, which involves inserting print statements to trace and analysing logs for fixing the bug. We collect a Leetcode problem dataset and evaluate our method using the Leetcode online judging system. Experiments with GPT-4 demonstrate the effectiveness of our approach, outperforming rubber duck debugging in easy and medium-level Leetcode problems by 1.5% and 17.9%.

Question generation (QG) is a natural language generation task where a model is trained to ask questions corresponding to some input text. Most recent approaches frame QG as a sequence-to-sequence problem and rely on additional features and mechanisms to increase performance; however, these often increase model complexity, and can rely on auxiliary data unavailable in practical use. A single Transformer-based unidirectional language model leveraging transfer learning can be used to produce high quality questions while disposing of additional task-specific complexity. Our QG model, finetuned from GPT-2 Small, outperforms several paragraph-level QG baselines on the SQuAD dataset by 0.95 METEOR points. Human evaluators rated questions as easy to answer, relevant to their context paragraph, and corresponding well to natural human speech. Also introduced is a new set of baseline scores on the RACE dataset, which has not previously been used for QG tasks. Further experimentation with varying model capacities and datasets with non-identification type questions is recommended in order to further verify the robustness of pretrained Transformer-based LMs as question generators.

Constructing large-scale datasets for the GitHub issue resolution task is crucial for both training and evaluating the software engineering capabilities of Large Language Models (LLMs). However, the traditional process for creating such benchmarks is notoriously challenging and labor-intensive, particularly in the stages of setting up evaluation environments, grading test outcomes, and validating task instances. In this paper, we propose SWE-Factory, an automated pipeline designed to address these challenges. To tackle these issues, our pipeline integrates three core automated components. First, we introduce SWE-Builder, a multi-agent system that automates evaluation environment construction, which employs four specialized agents that work in a collaborative, iterative loop and leverages an environment memory pool to enhance efficiency. Second, we introduce a standardized, exit-code-based grading method that eliminates the need for manually writing custom parsers. Finally, we automate the fail2pass validation process using these reliable exit code signals. Experiments on 671 issues across four programming languages show that our pipeline can effectively construct valid task instances; for example, with GPT-4.1-mini, our SWE-Builder constructs 269 valid instances at 0.045 per instance, while with Gemini-2.5-flash, it achieves comparable performance at the lowest cost of 0.024 per instance. We also demonstrate that our exit-code-based grading achieves 100% accuracy compared to manual inspection, and our automated fail2pass validation reaches a precision of 0.92 and a recall of 1.00. We hope our automated pipeline will accelerate the collection of large-scale, high-quality GitHub issue resolution datasets for both training and evaluation. Our code and datasets are released at https://github.com/DeepSoftwareAnalytics/swe-factory.

Assurance cases can be used to argue for the safety of products in safety engineering. In safety-critical areas, the construction of assurance cases is indispensable. Trustworthiness Derivation Trees (TDTs) enhance assurance cases by incorporating formal methods, rendering it possible for automatic reasoning about assurance cases. We present Trustworthiness Derivation Tree Analyzer (Trusta), a desktop application designed to automatically construct and verify TDTs. The tool has a built-in Prolog interpreter in its backend, and is supported by the constraint solvers Z3 and MONA. Therefore, it can solve constraints about logical formulas involving arithmetic, sets, Horn clauses etc. Trusta also utilizes large language models to make the creation and evaluation of assurance cases more convenient. It allows for interactive human examination and modification. We evaluated top language models like ChatGPT-3.5, ChatGPT-4, and PaLM 2 for generating assurance cases. Our tests showed a 50%-80% similarity between machine-generated and human-created cases. In addition, Trusta can extract formal constraints from text in natural languages, facilitating an easier interpretation and validation process. This extraction is subject to human review and correction, blending the best of automated efficiency with human insight. To our knowledge, this marks the first integration of large language models in automatic creating and reasoning about assurance cases, bringing a novel approach to a traditional challenge. Through several industrial case studies, Trusta has proven to quickly find some subtle issues that are typically missed in manual inspection, demonstrating its practical value in enhancing the assurance case development process.

Retrieval augmented generation (RAG) enhances the accuracy and reliability of generative AI models by sourcing factual information from external databases, which is extensively employed in document-grounded question-answering (QA) tasks. Off-the-shelf RAG flows are well pretrained on general-purpose documents, yet they encounter significant challenges when being applied to knowledge-intensive vertical domains, such as electronic design automation (EDA). This paper addresses such issue by proposing a customized RAG framework along with three domain-specific techniques for EDA tool documentation QA, including a contrastive learning scheme for text embedding model fine-tuning, a reranker distilled from proprietary LLM, and a generative LLM fine-tuned with high-quality domain corpus. Furthermore, we have developed and released a documentation QA evaluation benchmark, ORD-QA, for OpenROAD, an advanced RTL-to-GDSII design platform. Experimental results demonstrate that our proposed RAG flow and techniques have achieved superior performance on ORD-QA as well as on a commercial tool, compared with state-of-the-arts. The ORD-QA benchmark and the training dataset for our customized RAG flow are open-source at https://github.com/lesliepy99/RAG-EDA.

Enabling Large Language Models (LLMs) to handle a wider range of complex tasks (e.g., coding, math) has drawn great attention from many researchers. As LLMs continue to evolve, merely increasing the number of model parameters yields diminishing performance improvements and heavy computational costs. Recently, OpenAI's o1 model has shown that inference strategies (i.e., Test-time Compute methods) can also significantly enhance the reasoning capabilities of LLMs. However, the mechanisms behind these methods are still unexplored. In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i.e., math, coding, commonsense reasoning). Specifically, first, our experiments show that the o1 model has achieved the best performance on most datasets. Second, as for the methods of searching diverse responses (e.g., BoN), we find the reward models' capability and the search space both limit the upper boundary of these methods. Third, as for the methods that break the problem into many sub-problems, the Agent Workflow has achieved better performance than Step-wise BoN due to the domain-specific system prompt for planning better reasoning processes. Fourth, it is worth mentioning that we have summarized six reasoning patterns of o1, and provided a detailed analysis on several reasoning benchmarks.

Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems. However, this repeated independent process often leads to the same mistakes, making the selected solution still incorrect. We propose a novel prompting method named Stepwise Correction (StepCo) that helps LLMs identify and revise incorrect steps in their generated reasoning paths. It iterates verification and revision phases that employ a process-supervised verifier. The verify-then-revise process not only improves answer correctness but also reduces token consumption with fewer paths needed to generate. With StepCo, a series of LLMs demonstrate exceptional performance. Notably, using GPT-4o as the backend LLM, StepCo achieves an average accuracy of 94.1 across eight datasets, significantly outperforming the state-of-the-art Best-of-N method by +2.4, while reducing token consumption by 77.8%.

Large Language Models (LLMs) excel at code generation, but ensuring their outputs to be functionally correct, especially in complex programming tasks, is a persistent challenge. While traditional Test-Driven Development (TDD) offers a path for code refinement, its efficacy with LLMs is often undermined by the scarcity of high-quality test cases or the pitfalls of automated test generation, including biased tests or inaccurate output predictions that can misdirect the correction process. This paper introduces Property-Generated Solver, a novel framework that leverages Property-Based Testing (PBT) to validate high-level program properties or invariants, instead of relying on specific input-output examples. These properties are often simpler to define and verify than directly predicting exhaustive test oracles, breaking the "cycle of self-deception" where tests might share flaws with the code they are meant to validate. Property-Generated Solver employs two collaborative LLM-based agents: a Generator dedicated to code generation and iterative refinement, and a Tester that manages the PBT life-cycle and formulate semantically rich feedback from property violations. The resulting comprehensive and actionable feedback then guides the Generator in its refinement efforts. By establishing PBT as the core validation engine within this iterative, closed-loop paradigm, Property-Generated Solver provides a robust mechanism for steering LLMs towards more correct and generalizable code. Extensive experimental results on multiple code generation benchmarks demonstrate that Property-Generated Solver achieves substantial pass@1 improvements, ranging from 23.1% to 37.3% relative gains over established TDD methods.

Decision-making, a complicated task requiring various types of abilities, presents an excellent framework for assessing Large Language Models (LLMs). Our research investigates LLMs' decision-making capabilities through the lens of a well-established field, Game Theory. We focus specifically on games that support the participation of more than two agents simultaneously. Subsequently, we introduce our framework, GAMA-Bench, including eight classical multi-agent games. We design a scoring scheme to assess a model's performance in these games quantitatively. Through GAMA-Bench, we investigate LLMs' robustness, generalizability, and enhancement strategies. Results reveal that while GPT-3.5 shows satisfying robustness, its generalizability is relatively limited. However, its performance can be improved through approaches such as Chain-of-Thought. Additionally, we conduct evaluations across various LLMs and find that GPT-4 outperforms other models on GAMA-Bench, achieving a score of 60.5. Moreover, Gemini-1.0-Pro and GPT-3.5 (0613, 1106, 0125) demonstrate similar intelligence on GAMA-Bench. The code and experimental results are made publicly available via https://github.com/CUHK-ARISE/GAMABench.

Test-Time Scaling (TTS) methods for enhancing Large Language Model (LLM) reasoning often incur substantial computational costs, primarily due to extensive reliance on external Process Reward Models (PRMs) or sampling methods like Best-of-N (BoN). This paper introduces Guided by Gut (GG), an efficient self-guided TTS framework that achieves PRM-level performance without costly external verifier models. Our method employs a lightweight tree search guided solely by intrinsic LLM signals, token-level confidence and step novelty. One critical innovation is improving the reliability of internal confidence estimates via a targeted reinforcement learning fine-tuning phase. Empirical evaluations on challenging mathematical reasoning benchmarks demonstrate that GG enables smaller models (e.g., 1.5B parameters) to achieve accuracy matching or surpassing significantly larger models (e.g., 32B-70B parameters), while reducing GPU memory usage by up to 10x. Compared to PRM-based methods, GG achieves comparable accuracy with 8x faster inference speeds and 4-5x lower memory usage. Additionally, GG reduces KV cache memory usage by approximately 50% compared to the BoN strategy, facilitating more efficient and practical deployment of TTS techniques.

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We consider real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. We therefore introduce SWE-bench, an evaluation framework including 2,294 software engineering problems drawn from real GitHub issues and corresponding pull requests across 12 popular Python repositories. Given a codebase along with a description of an issue to be resolved, a language model is tasked with editing the codebase to address the issue. Resolving issues in SWE-bench frequently requires understanding and coordinating changes across multiple functions, classes, and even files simultaneously, calling for models to interact with execution environments, process extremely long contexts and perform complex reasoning that goes far beyond traditional code generation. Our evaluations show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues. Claude 2 and GPT-4 solve a mere 4.8% and 1.7% of instances respectively, even when provided with an oracle retriever. Advances on SWE-bench represent steps towards LMs that are more practical, intelligent, and autonomous.

Since the launch of ChatGPT at the end of 2022, generative dialogue models represented by ChatGPT have quickly become essential tools in daily life. As user expectations increase, enhancing the capability of generative dialogue models to solve complex problems has become a focal point of current research. This paper delves into the effectiveness of the RAFT (Retrieval Augmented Fine-Tuning) method in improving the performance of Generative dialogue models. RAFT combines chain-of-thought with model supervised fine-tuning (SFT) and retrieval augmented generation (RAG), which significantly enhanced the model's information extraction and logical reasoning abilities. We evaluated the RAFT method across multiple datasets and analysed its performance in various reasoning tasks, including long-form QA and short-form QA tasks, tasks in both Chinese and English, and supportive and comparison reasoning tasks. Notably, it addresses the gaps in previous research regarding long-form QA tasks and Chinese datasets. Moreover, we also evaluate the benefit of the chain-of-thought (CoT) in the RAFT method. This work offers valuable insights for studies focused on enhancing the performance of generative dialogue models.

This study investigates various approaches to using Large Language Models (LLMs) for Text-to-SQL program synthesis, focusing on the outcomes and insights derived. Employing the popular Text-to-SQL dataset, spider, the goal was to input a natural language question along with the database schema and output the correct SQL SELECT query. The initial approach was to fine-tune a local and open-source model to generate the SELECT query. After QLoRa fine-tuning WizardLM's WizardCoder-15B model on the spider dataset, the execution accuracy for generated queries rose to a high of 61%. With the second approach, using the fine-tuned gpt-3.5-turbo-16k (Few-shot) + gpt-4-turbo (Zero-shot error correction), the execution accuracy reached a high of 82.1%. Of all the incorrect queries, most can be categorized into a seven different categories of what went wrong: selecting the wrong columns or wrong order of columns, grouping by the wrong column, predicting the wrong values in conditionals, using different aggregates than the ground truth, extra or too few JOIN clauses, inconsistencies in the Spider dataset, and lastly completely incorrect query structure. Most if not all of the queries fall into these categories and it is insightful to understanding where the faults still lie with LLM program synthesis and where they can be improved.

Background: General-purpose large language models that utilize both text and images have not been evaluated on a diverse array of challenging medical cases. Methods: Using 934 cases from the NEJM Image Challenge published between 2005 and 2023, we evaluated the accuracy of the recently released Generative Pre-trained Transformer 4 with Vision model (GPT-4V) compared to human respondents overall and stratified by question difficulty, image type, and skin tone. We further conducted a physician evaluation of GPT-4V on 69 NEJM clinicopathological conferences (CPCs). Analyses were conducted for models utilizing text alone, images alone, and both text and images. Results: GPT-4V achieved an overall accuracy of 61% (95% CI, 58 to 64%) compared to 49% (95% CI, 49 to 50%) for humans. GPT-4V outperformed humans at all levels of difficulty and disagreement, skin tones, and image types; the exception was radiographic images, where performance was equivalent between GPT-4V and human respondents. Longer, more informative captions were associated with improved performance for GPT-4V but similar performance for human respondents. GPT-4V included the correct diagnosis in its differential for 80% (95% CI, 68 to 88%) of CPCs when using text alone, compared to 58% (95% CI, 45 to 70%) of CPCs when using both images and text. Conclusions: GPT-4V outperformed human respondents on challenging medical cases and was able to synthesize information from both images and text, but performance deteriorated when images were added to highly informative text. Overall, our results suggest that multimodal AI models may be useful in medical diagnostic reasoning but that their accuracy may depend heavily on context.

Large Language Models (LLMs) in Software Engineering (SE) can offer assistance for coding. To facilitate a rigorous evaluation of LLMs in practical coding contexts, Carlos et al. introduced the SWE-bench dataset, which comprises 2,294 real-world GitHub issues and their corresponding pull requests, collected from 12 widely used Python repositories. Several impressive LLM-based toolkits recently are developed and evaluated on this dataset. However, a systematic evaluation of the quality of SWE-bench remains missing. In this paper, we addressed this gap by presenting an empirical analysis of the SWE-bench dataset. We conducted a manual screening of instances where SWEAgent + GPT-4 successfully resolved issues by comparing the model-generated patches with the actual pull requests. SWE-Agent+GPT-4 was at the top of SWE-bench leaderboard during the time of our study. Our analysis reveals some critical issues with the SWE-bench dataset: 1) 32.67% of the successful patches involve cheating as the solutions were directly provided in the issue report or the comments. We refer to as solution leakage problem. 2) 31.08% of the passed patches are suspicious patches due to weak test cases, i.e., the tests were not adequate to verify the correctness of a patch. When we filtered out these problematic issues, the resolution rate of SWE-Agent+GPT-4 dropped from 12.47% to 3.97%. We also observed that the same data quality issues also exist in the two variants of SWE-bench, i.e., SWE-bench Lite and SWE-Bench Verified. In addition, over 94% of the issues were created before LLM's knowledge cutoff dates, posing potential data leakage issues.

This paper presents the second ChatGPT4PCG competition at the 2024 IEEE Conference on Games. In this edition of the competition, we follow the first edition, but make several improvements and changes. We introduce a new evaluation metric along with allowing a more flexible format for participants' submissions and making several improvements to the evaluation pipeline. Continuing from the first edition, we aim to foster and explore the realm of prompt engineering (PE) for procedural content generation (PCG). While the first competition saw success, it was hindered by various limitations; we aim to mitigate these limitations in this edition. We introduce diversity as a new metric to discourage submissions aimed at producing repetitive structures. Furthermore, we allow submission of a Python program instead of a prompt text file for greater flexibility in implementing advanced PE approaches, which may require control flow, including conditions and iterations. We also make several improvements to the evaluation pipeline with a better classifier for similarity evaluation and better-performing function signatures. We thoroughly evaluate the effectiveness of the new metric and the improved classifier. Additionally, we perform an ablation study to select a function signature to instruct ChatGPT for level generation. Finally, we provide implementation examples of various PE techniques in Python and evaluate their preliminary performance. We hope this competition serves as a resource and platform for learning about PE and PCG in general.

We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex powers GitHub Copilot. On HumanEval, a new evaluation set we release to measure functional correctness for synthesizing programs from docstrings, our model solves 28.8% of the problems, while GPT-3 solves 0% and GPT-J solves 11.4%. Furthermore, we find that repeated sampling from the model is a surprisingly effective strategy for producing working solutions to difficult prompts. Using this method, we solve 70.2% of our problems with 100 samples per problem. Careful investigation of our model reveals its limitations, including difficulty with docstrings describing long chains of operations and with binding operations to variables. Finally, we discuss the potential broader impacts of deploying powerful code generation technologies, covering safety, security, and economics.

Large Language Models have demonstrated exceptional proficiency on coding tasks, but it is challenging to precisely evaluate their code reasoning ability. Existing benchmarks are insufficient as they are unrealistic and conflate semantic reasoning ability with performance on software engineering tasks. We introduce CRQBench, a benchmark of 100 C++ code reasoning questions and answers derived from contextualized code review comments. To curate CRQBench, we use an LLM assistant alongside human inspection, reducing manual effort. We conduct an evaluation of GPT-4 on CRQBench and find that it produces correct responses grounded in the given context for 65 of the 100 questions.

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely employed, recent research has demonstrated the limitations of using sequence-level probability estimates given by LLMs as reliable indicators of generation quality. Conversely, LLMs have demonstrated strong calibration at the token level, particularly when it comes to choosing correct answers in multiple-choice questions or evaluating true/false statements. In this work, we reformulate open-ended generation tasks into token-level prediction tasks, and leverage LLMs' superior calibration at the token level. We instruct an LLM to self-evaluate its answers, employing either a multi-way comparison or a point-wise evaluation approach, with the option to include a ``None of the above'' option to express the model's uncertainty explicitly. We benchmark a range of scoring methods based on self-evaluation and evaluate their performance in selective generation using TruthfulQA and TL;DR. Through experiments with PaLM-2 and GPT-3, we demonstrate that self-evaluation based scores not only improve accuracy, but also correlate better with the overall quality of generated content.

Multilingual Natural Language Generation (NLG) is challenging due to the lack of training data for low-resource languages. However, some low-resource languages have up to tens of millions of speakers globally, making it important to improve NLG tools for them. Table-to-Text NLG is an excellent measure of models' reasoning abilities but is very challenging in the multilingual setting. System outputs are often not attributable, or faithful, to the data in the source table. Intermediate planning techniques like Question-Answer (QA) blueprints have been shown to improve attributability on summarisation tasks. This work explores whether QA blueprints make multilingual Table-to-Text outputs more attributable to the input tables. This paper extends the challenging multilingual Table-to-Text dataset, TaTA, which includes African languages, with QA blueprints. Sequence-to-sequence language models are then finetuned on this dataset, with and without blueprints. Results show that QA blueprints improve performance for models finetuned and evaluated only on English examples, but do not demonstrate gains in the multilingual setting. This is due to inaccuracies in machine translating the blueprints from English into target languages when generating the training data, and models failing to rely closely on the blueprints they generate. An in-depth analysis is conducted on why this is challenging.

LLMs have shown impressive progress in robotics (e.g., manipulation and navigation) with natural language task descriptions. The success of LLMs in these tasks leads us to wonder: What is the ability of LLMs to solve vehicle routing problems (VRPs) with natural language task descriptions? In this work, we study this question in three steps. First, we construct a dataset with 21 types of single- or multi-vehicle routing problems. Second, we evaluate the performance of LLMs across four basic prompt paradigms of text-to-code generation, each involving different types of text input. We find that the basic prompt paradigm, which generates code directly from natural language task descriptions, performs the best for GPT-4, achieving 56% feasibility, 40% optimality, and 53% efficiency. Third, based on the observation that LLMs may not be able to provide correct solutions at the initial attempt, we propose a framework that enables LLMs to refine solutions through self-reflection, including self-debugging and self-verification. With GPT-4, our proposed framework achieves a 16% increase in feasibility, a 7% increase in optimality, and a 15% increase in efficiency. Moreover, we examine the sensitivity of GPT-4 to task descriptions, specifically focusing on how its performance changes when certain details are omitted from the task descriptions, yet the core meaning is preserved. Our findings reveal that such omissions lead to a notable decrease in performance: 4% in feasibility, 4% in optimality, and 5% in efficiency. Website: https://sites.google.com/view/words-to-routes/

Finetuning specialized generative evaluators has emerged as a popular paradigm to meet the increasing demand for scalable evaluation during both training and test-time. However, recent work has largely focused on applying new methodology, such as reinforcement learning (RL), to training evaluators, shying away from large-scale, data-driven development. In this work, we focus on data scaling, curating a set of 2.5M samples spanning five unique evaluation tasks (pairwise, step-level, reference-free and reference-based verification, and single rating) and multiple domains focused on reasoning evaluation. With our data, we train Foundational Automatic Reasoning Evaluators (FARE), a family of 8B and 20B (with 3.6B active) parameter evaluators, with a simple iterative rejection-sampling supervised finetuning (SFT) approach. FARE-8B challenges larger specialized RL-trained evaluators and FARE-20B sets the new standard for open-source evaluators, surpassing specialized 70B+ evaluators. Beyond static benchmarks, we evaluate FARE in real-world tasks: As inference-time rerankers, FARE-20B achieves near-oracle performance on MATH. As verifiers in RL training, FARE improves the downstream RL-trained model performance by up to 14.1% vs. string-matching verifiers. When initialized from FARE, a continually-finetuned FARE-Code outperforms gpt-oss-20B by 65% on evaluating test-case quality.

We propose an iterative programmatic planning (IPP) framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code using large language models (LLMs). Instead of relying on traditional search or reinforcement learning, our approach uses code generation as policy synthesis, where the LLM outputs executable programs that map environment states to action sequences. Our proposed architecture incorporates several prompting strategies, including direct code generation, pseudocode-conditioned refinement, and curriculum-based prompting, but also includes an iterative refinement mechanism that updates code based on task performance feedback. We evaluate our approach using six leading LLMs and two challenging grid-based benchmarks (GRASP and MiniGrid). Our IPP framework demonstrates improvements over direct code generation ranging from 10\% to as much as 10x across five of the six models and establishes a new state-of-the-art result for GRASP. IPP is found to significantly outperform direct elicitation of a solution from GPT-o3-mini (by 63\% on MiniGrid to 116\% on GRASP), demonstrating the viability of the overall approach. Computational costs of all code generation approaches are similar. While code generation has a higher initial prompting cost compared to direct solution elicitation (\0.08 per task vs. 0.002 per instance for GPT-o3-mini), the code can be reused for any number of instances, making the amortized cost significantly lower (by 400x on GPT-o3-mini across the complete GRASP benchmark).

This paper reviews the state-of-the-art of language models architectures and strategies for "complex" question-answering (QA, CQA, CPS) with a focus on hybridization. Large Language Models (LLM) are good at leveraging public data on standard problems but once you want to tackle more specific complex questions or problems (e.g. How does the concept of personal freedom vary between different cultures ? What is the best mix of power generation methods to reduce climate change ?) you may need specific architecture, knowledge, skills, methods, sensitive data protection, explainability, human approval and versatile feedback... Recent projects like ChatGPT and GALACTICA have allowed non-specialists to grasp the great potential as well as the equally strong limitations of LLM in complex QA. In this paper, we start by reviewing required skills and evaluation techniques. We integrate findings from the robust community edited research papers BIG, BLOOM and HELM which open source, benchmark and analyze limits and challenges of LLM in terms of tasks complexity and strict evaluation on accuracy (e.g. fairness, robustness, toxicity, ...) as a baseline. We discuss some challenges associated with complex QA, including domain adaptation, decomposition and efficient multi-step QA, long form and non-factoid QA, safety and multi-sensitivity data protection, multimodal search, hallucinations, explainability and truthfulness, temporal reasoning. We analyze current solutions and promising research trends, using elements such as: hybrid LLM architectural patterns, training and prompting strategies, active human reinforcement learning supervised with AI, neuro-symbolic and structured knowledge grounding, program synthesis, iterated decomposition and others.

Quantum algorithms, represented as quantum circuits, can be used as benchmarks for assessing the performance of quantum systems. Existing datasets, widely utilized in the field, suffer from limitations in size and versatility, leading researchers to employ randomly generated circuits. Random circuits are, however, not representative benchmarks as they lack the inherent properties of real quantum algorithms for which the quantum systems are manufactured. This shortage of `useful' quantum benchmarks poses a challenge to advancing the development and comparison of quantum compilers and hardware. This research aims to enhance the existing quantum circuit datasets by generating what we refer to as `realistic-looking' circuits by employing the Transformer machine learning architecture. For this purpose, we introduce KetGPT, a tool that generates synthetic circuits in OpenQASM language, whose structure is based on quantum circuits derived from existing quantum algorithms and follows the typical patterns of human-written algorithm-based code (e.g., order of gates and qubits). Our three-fold verification process, involving manual inspection and Qiskit framework execution, transformer-based classification, and structural analysis, demonstrates the efficacy of KetGPT in producing large amounts of additional circuits that closely align with algorithm-based structures. Beyond benchmarking, we envision KetGPT contributing substantially to AI-driven quantum compilers and systems.

Large language models (LLMs) such as ChatGPT and GPT-4 have made significant progress in NLP. However, their ability to memorize, represent, and leverage commonsense knowledge has been a well-known pain point for LLMs. It remains unclear that: (1) Can GPTs effectively answer commonsense questions? (2) Are GPTs knowledgeable in commonsense? (3) Are GPTs aware of the underlying commonsense knowledge for answering a specific question? (4) Can GPTs effectively leverage commonsense for answering questions? To evaluate the above commonsense problems, we conduct a series of experiments to evaluate ChatGPT's commonsense abilities, and the experimental results show that: (1) GPTs can achieve good QA accuracy in commonsense tasks, while they still struggle with certain types of knowledge. (2) ChatGPT is knowledgeable, and can accurately generate most of the commonsense knowledge using knowledge prompts. (3) Despite its knowledge, ChatGPT is an inexperienced commonsense problem solver, which cannot precisely identify the needed commonsense knowledge for answering a specific question, i.e., ChatGPT does not precisely know what commonsense knowledge is required to answer a question. The above findings raise the need to investigate better mechanisms for utilizing commonsense knowledge in LLMs, such as instruction following, better commonsense guidance, etc.

Commit message generation (CMG) is a crucial task in software engineering that is challenging to evaluate correctly. When a CMG system is integrated into the IDEs and other products at JetBrains, we perform online evaluation based on user acceptance of the generated messages. However, performing online experiments with every change to a CMG system is troublesome, as each iteration affects users and requires time to collect enough statistics. On the other hand, offline evaluation, a prevalent approach in the research literature, facilitates fast experiments but employs automatic metrics that are not guaranteed to represent the preferences of real users. In this work, we describe a novel way we employed to deal with this problem at JetBrains, by leveraging an online metric - the number of edits users introduce before committing the generated messages to the VCS - to select metrics for offline experiments. To support this new type of evaluation, we develop a novel markup collection tool mimicking the real workflow with a CMG system, collect a dataset with 57 pairs consisting of commit messages generated by GPT-4 and their counterparts edited by human experts, and design and verify a way to synthetically extend such a dataset. Then, we use the final dataset of 656 pairs to study how the widely used similarity metrics correlate with the online metric reflecting the real users' experience. Our results indicate that edit distance exhibits the highest correlation, whereas commonly used similarity metrics such as BLEU and METEOR demonstrate low correlation. This contradicts the previous studies on similarity metrics for CMG, suggesting that user interactions with a CMG system in real-world settings differ significantly from the responses by human labelers operating within controlled research environments. We release all the code and the dataset for researchers: https://jb.gg/cmg-evaluation.

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM code/text generation. We construct a comprehensive benchmark SymBench comprising 37 symbolic tasks with adjustable complexity and also synthesize datasets of 12k multi-round guidance/generation trajectories and 5.5k guidance comparison pairs. We fine-tune the Llama-3-8B model with a newly designed multi-round supervised fine-tuning (SFT) and direct preference optimization (DPO). The resulting model, CodeSteerLLM, augmented with the proposed symbolic and self-answer checkers, effectively guides the code/text generation of larger models. Augmenting GPT-4o with CodeSteer raises its average performance score from 53.3 to 86.4, even outperforming the existing best LLM OpenAI o1 (82.7), o1-preview (74.8), and DeepSeek R1 (76.8) across all 37 tasks (28 seen, 9 unseen). Trained for GPT-4o, CodeSteer demonstrates superior generalizability, providing an average 41.8 performance boost on Claude, Mistral, and GPT-3.5. CodeSteer-guided LLMs fully harness symbolic computing to maintain strong performance on highly complex tasks. Models, Datasets, and Codes are available at https://github.com/yongchao98/CodeSteer-v1.0.

Code generation problems differ from common natural language problems - they require matching the exact syntax of the target language, identifying happy paths and edge cases, paying attention to numerous small details in the problem spec, and addressing other code-specific issues and requirements. Hence, many of the optimizations and tricks that have been successful in natural language generation may not be effective for code tasks. In this work, we propose a new approach to code generation by LLMs, which we call AlphaCodium - a test-based, multi-stage, code-oriented iterative flow, that improves the performances of LLMs on code problems. We tested AlphaCodium on a challenging code generation dataset called CodeContests, which includes competitive programming problems from platforms such as Codeforces. The proposed flow consistently and significantly improves results. On the validation set, for example, GPT-4 accuracy (pass@5) increased from 19% with a single well-designed direct prompt to 44% with the AlphaCodium flow. Many of the principles and best practices acquired in this work, we believe, are broadly applicable to general code generation tasks. Full implementation is available at: https://github.com/Codium-ai/AlphaCodium

Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global planning absence to structure multi-step reasoning, and (ii) unfaithful execution, which hinders effective query formulation and consistent use of retrieved evidence. We propose GlobalRAG, a reinforcement learning framework designed to enhance global reasoning in multi-hop QA. GlobalRAG decomposes questions into subgoals, coordinates retrieval with reasoning, and refines evidence iteratively. To guide this process, we introduce Planning Quality Reward and SubGoal Completion Reward, which encourage coherent planning and reliable subgoal execution. In addition, a progressive weight annealing strategy balances process-oriented and outcome-based objectives. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that GlobalRAG significantly outperforms strong baselines while using only 8k training data (42% of the training data used by strong baselines), achieving average improvements of 14.2% in both EM and F1.

Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In contrast, this paper introduces a Video Understanding and Reasoning Framework (VURF) based on the reasoning power of LLMs. Ours is a novel approach to extend the utility of LLMs in the context of video tasks, leveraging their capacity to generalize from minimal input and output demonstrations within a contextual framework. By presenting LLMs with pairs of instructions and their corresponding high-level programs, we harness their contextual learning capabilities to generate executable visual programs for video understanding. To enhance program's accuracy and robustness, we implement two important strategies. Firstly, we employ a feedback-generation approach, powered by GPT-3.5, to rectify errors in programs utilizing unsupported functions. Secondly, taking motivation from recent works on self refinement of LLM outputs, we introduce an iterative procedure for improving the quality of the in-context examples by aligning the initial outputs to the outputs that would have been generated had the LLM not been bound by the structure of the in-context examples. Our results on several video-specific tasks, including visual QA, video anticipation, pose estimation and multi-video QA illustrate the efficacy of these enhancements in improving the performance of visual programming approaches for video tasks. Our Codes and data will be publicly released.

We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert transformer architecture and are trained using large-scale distillation and reinforcement learning. We optimize the models to have strong agentic capabilities (deep research browsing, python tool use, and support for developer-provided functions), all while using a rendered chat format that enables clear instruction following and role delineation. Both models achieve strong results on benchmarks ranging from mathematics, coding, and safety. We release the model weights, inference implementations, tool environments, and tokenizers under an Apache 2.0 license to enable broad use and further research.

The GitHub issue resolution task aims to resolve issues reported in repositories automatically. With advances in large language models (LLMs), this task has gained increasing attention, and several benchmarks are proposed to evaluate the issue resolution ability of LLMs. However, existing benchmarks have three main limitations. First, current benchmarks focus on a single programming language, limiting the evaluation of issues from repositories across different languages. Second, they usually cover a narrow range of domains, which may fail to represent the diversity of real-world issues. Third, existing benchmarks rely solely on textual information in issue descriptions, overlooking multimodal information such as images in issues. In this paper, we propose OmniGIRL, a GitHub Issue ResoLution benchmark that is multilingual, multimodal, and multi-domain. OmniGIRL includes 959 task instances, which are collected from repositories across four programming languages (i.e., Python, JavaScript, TypeScript, and Java) and eight different domains. Our evaluation shows that current LLMs show limited performances on OmniGIRL. Notably, the best-performing model, GPT-4o, resolves only 8.6% of the issues. Besides, we find that current LLMs struggle to resolve issues requiring understanding images. The best performance is achieved by Claude-3.5-Sonnet, which resolves only 10.5% of the issues with image information. Finally, we analyze the reasons behind current LLMs' failure on OmniGIRL, providing insights for future improvements.

Large Language Models (LLMs) have demonstrated impressive zero shot performance on a wide range of NLP tasks, demonstrating the ability to reason and apply commonsense. A relevant application is to use them for creating high quality synthetic datasets for downstream tasks. In this work, we probe whether GPT-4 can be used to augment existing extractive reading comprehension datasets. Automating data annotation processes has the potential to save large amounts of time, money and effort that goes into manually labelling datasets. In this paper, we evaluate the performance of GPT-4 as a replacement for human annotators for low resource reading comprehension tasks, by comparing performance after fine tuning, and the cost associated with annotation. This work serves to be the first analysis of LLMs as synthetic data augmenters for QA systems, highlighting the unique opportunities and challenges. Additionally, we release augmented versions of low resource datasets, that will allow the research community to create further benchmarks for evaluation of generated datasets.

This paper introduces fourteen novel datasets for the evaluation of Large Language Models' safety in the context of enterprise tasks. A method was devised to evaluate a model's safety, as determined by its ability to follow instructions and output factual, unbiased, grounded, and appropriate content. In this research, we used OpenAI GPT as point of comparison since it excels at all levels of safety. On the open-source side, for smaller models, Meta Llama2 performs well at factuality and toxicity but has the highest propensity for hallucination. Mistral hallucinates the least but cannot handle toxicity well. It performs well in a dataset mixing several tasks and safety vectors in a narrow vertical domain. Gemma, the newly introduced open-source model based on Google Gemini, is generally balanced but trailing behind. When engaging in back-and-forth conversation (multi-turn prompts), we find that the safety of open-source models degrades significantly. Aside from OpenAI's GPT, Mistral is the only model that still performed well in multi-turn tests.

Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and user-interaction feedback, current code agents rely only on simple code execution for feedback and verification. This approach fails to capture the actual quality of the generated code. In this paper, we propose WebGen-Agent, a novel website-generation agent that leverages comprehensive and multi-level visual feedback to iteratively generate and refine the website codebase. Detailed and expressive text descriptions and suggestions regarding the screenshots and GUI-agent testing of the websites are generated by a visual language model (VLM), together with scores that quantify their quality. The screenshot and GUI-agent scores are further integrated with a backtracking and select-best mechanism, enhancing the performance of the agent. Utilizing the accurate visual scores inherent in the WebGen-Agent workflow, we further introduce Step-GRPO with Screenshot and GUI-agent Feedback to improve the ability of LLMs to act as the reasoning engine of WebGen-Agent. By using the screenshot and GUI-agent scores at each step as the reward in Step-GRPO, we provide a dense and reliable process supervision signal, which effectively improves the model's website-generation ability. On the WebGen-Bench dataset, WebGen-Agent increases the accuracy of Claude-3.5-Sonnet from 26.4% to 51.9% and its appearance score from 3.0 to 3.9, outperforming the previous state-of-the-art agent system. Additionally, our Step-GRPO training approach increases the accuracy of Qwen2.5-Coder-7B-Instruct from 38.9% to 45.4% and raises the appearance score from 3.4 to 3.7.

Recent years have witnessed a significant interest in developing large multimodal models (LMMs) capable of performing various visual reasoning and understanding tasks. This has led to the introduction of multiple LMM benchmarks to evaluate LMMs on different tasks. However, most existing LMM evaluation benchmarks are predominantly English-centric. In this work, we develop a comprehensive LMM evaluation benchmark for the Arabic language to represent a large population of over 400 million speakers. The proposed benchmark, named CAMEL-Bench, comprises eight diverse domains and 38 sub-domains including, multi-image understanding, complex visual perception, handwritten document understanding, video understanding, medical imaging, plant diseases, and remote sensing-based land use understanding to evaluate broad scenario generalizability. Our CAMEL-Bench comprises around 29,036 questions that are filtered from a larger pool of samples, where the quality is manually verified by native speakers to ensure reliable model assessment. We conduct evaluations of both closed-source, including GPT-4 series, and open-source LMMs. Our analysis reveals the need for substantial improvement, especially among the best open-source models, with even the closed-source GPT-4o achieving an overall score of 62%. Our benchmark and evaluation scripts are open-sourced.

We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily on organic data sources such as web content or code, phi-4 strategically incorporates synthetic data throughout the training process. While previous models in the Phi family largely distill the capabilities of a teacher model (specifically GPT-4), phi-4 substantially surpasses its teacher model on STEM-focused QA capabilities, giving evidence that our data-generation and post-training techniques go beyond distillation. Despite minimal changes to the phi-3 architecture, phi-4 achieves strong performance relative to its size -- especially on reasoning-focused benchmarks -- due to improved data, training curriculum, and innovations in the post-training scheme.

Bug reports are vital for software maintenance that allow users to inform developers of the problems encountered while using the software. As such, researchers have committed considerable resources toward automating bug replay to expedite the process of software maintenance. Nonetheless, the success of current automated approaches is largely dictated by the characteristics and quality of bug reports, as they are constrained by the limitations of manually-crafted patterns and pre-defined vocabulary lists. Inspired by the success of Large Language Models (LLMs) in natural language understanding, we propose AdbGPT, a new lightweight approach to automatically reproduce the bugs from bug reports through prompt engineering, without any training and hard-coding effort. AdbGPT leverages few-shot learning and chain-of-thought reasoning to elicit human knowledge and logical reasoning from LLMs to accomplish the bug replay in a manner similar to a developer. Our evaluations demonstrate the effectiveness and efficiency of our AdbGPT to reproduce 81.3% of bug reports in 253.6 seconds, outperforming the state-of-the-art baselines and ablation studies. We also conduct a small-scale user study to confirm the usefulness of AdbGPT in enhancing developers' bug replay capabilities.

This paper introduce LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We developed a systematic approach that organizes videos into a hierarchical tree structure and incorporates self-revision mechanisms to ensure high-quality QA pairs. Each QA pair in LongViTU features: 1) long-term context (average certificate length of 4.6 minutes); 2) rich knowledge and condensed reasoning (commonsense, causality, planning, etc.); and 3) explicit timestamp labels for relevant events. LongViTU also serves as a benchmark for instruction following in long-form and streaming video understanding. We evaluate the open-source state-of-the-art long video understanding model, LongVU, and the commercial model, Gemini-1.5-Pro, on our benchmark. They achieve GPT-4 scores of 49.9 and 52.3, respectively, underscoring the substantial challenge posed by our benchmark. Further supervised fine-tuning (SFT) on LongVU led to performance improvements of 12.0% on our benchmark, 2.2% on the in-distribution (ID) benchmark EgoSchema, 1.0%, 2.2% and 1.2% on the out-of-distribution (OOD) benchmarks VideoMME (Long), WorldQA and OpenEQA, respectively. These outcomes demonstrate LongViTU's high data quality and robust OOD generalizability.

Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise only a limited number of homogeneous test cases, resulting in subtle faults going undetected. This not only artificially inflates measured performance but also compromises accurate reward estimation in reinforcement learning frameworks utilizing verifiable rewards (RLVR). To address these critical shortcomings, we systematically investigate the test-case generation (TCG) task by proposing multi-dimensional metrics designed to rigorously quantify test-suite thoroughness. Furthermore, we introduce a human-LLM collaborative method (SAGA), leveraging human programming expertise with LLM reasoning capability, aimed at significantly enhancing both the coverage and the quality of generated test cases. In addition, we develop a TCGBench to facilitate the study of the TCG task. Experiments show that SAGA achieves a detection rate of 90.62% and a verifier accuracy of 32.58% on TCGBench. The Verifier Accuracy (Verifier Acc) of the code generation evaluation benchmark synthesized by SAGA is 10.78% higher than that of LiveCodeBench-v6. These results demonstrate the effectiveness of our proposed method. We hope this work contributes to building a scalable foundation for reliable LLM code evaluation, further advancing RLVR in code generation, and paving the way for automated adversarial test synthesis and adaptive benchmark integration.

Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q\&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75\% preference for GPT4All using CFG over baseline.

AI is undergoing a paradigm shift, with breakthroughs achieved by systems orchestrating multiple large language models (LLMs) and other complex components. As a result, developing principled and automated optimization methods for compound AI systems is one of the most important new challenges. Neural networks faced a similar challenge in its early days until backpropagation and automatic differentiation transformed the field by making optimization turn-key. Inspired by this, we introduce TextGrad, a powerful framework performing automatic ``differentiation'' via text. TextGrad backpropagates textual feedback provided by LLMs to improve individual components of a compound AI system. In our framework, LLMs provide rich, general, natural language suggestions to optimize variables in computation graphs, ranging from code snippets to molecular structures. TextGrad follows PyTorch's syntax and abstraction and is flexible and easy-to-use. It works out-of-the-box for a variety of tasks, where the users only provide the objective function without tuning components or prompts of the framework. We showcase TextGrad's effectiveness and generality across a diverse range of applications, from question answering and molecule optimization to radiotherapy treatment planning. Without modifying the framework, TextGrad improves the zero-shot accuracy of GPT-4o in Google-Proof Question Answering from 51% to 55%, yields 20% relative performance gain in optimizing LeetCode-Hard coding problem solutions, improves prompts for reasoning, designs new druglike small molecules with desirable in silico binding, and designs radiation oncology treatment plans with high specificity. TextGrad lays a foundation to accelerate the development of the next-generation of AI systems.

We present a Japanese domain-specific language model for the pharmaceutical field, developed through continual pretraining on 2 billion Japanese pharmaceutical tokens and 8 billion English biomedical tokens. To enable rigorous evaluation, we introduce three new benchmarks: YakugakuQA, based on national pharmacist licensing exams; NayoseQA, which tests cross-lingual synonym and terminology normalization; and SogoCheck, a novel task designed to assess consistency reasoning between paired statements. We evaluate our model against both open-source medical LLMs and commercial models, including GPT-4o. Results show that our domain-specific model outperforms existing open models and achieves competitive performance with commercial ones, particularly on terminology-heavy and knowledge-based tasks. Interestingly, even GPT-4o performs poorly on SogoCheck, suggesting that cross-sentence consistency reasoning remains an open challenge. Our benchmark suite offers a broader diagnostic lens for pharmaceutical NLP, covering factual recall, lexical variation, and logical consistency. This work demonstrates the feasibility of building practical, secure, and cost-effective language models for Japanese domain-specific applications, and provides reusable evaluation resources for future research in pharmaceutical and healthcare NLP. Our model, codes, and datasets are released at https://github.com/EQUES-Inc/pharma-LLM-eval.

Recent advancements in Large Vision-Language Models are accelerating the development of Graphical User Interface (GUI) agents that utilize human-like vision perception capabilities to enhance productivity on digital devices. Compared to approaches predicated on GUI metadata, which are platform-dependent and vulnerable to implementation variations, vision-based approaches offer broader applicability. In this vision-based paradigm, the GUI instruction grounding, which maps user instruction to the location of corresponding element on the given screenshot, remains a critical challenge, particularly due to limited public training dataset and resource-intensive manual instruction data annotation. In this paper, we delve into unexplored challenges in this task including element-to-screen ratio, unbalanced element type, and implicit instruction. To address these challenges, we introduce a large-scale data synthesis pipeline UI-E2I-Synth for generating varying complex instruction datasets using GPT-4o instead of human annotators. Furthermore, we propose a new GUI instruction grounding benchmark UI-I2E-Bench, which is designed to address the limitations of existing benchmarks by incorporating diverse annotation aspects. Our model, trained on the synthesized data, achieves superior performance in GUI instruction grounding, demonstrating the advancements of proposed data synthesis pipeline. The proposed benchmark, accompanied by extensive analyses, provides practical insights for future research in GUI grounding. We will release corresponding artifacts at https://colmon46.github.io/i2e-bench-leaderboard/ .

We introduce meta-prompting, an effective scaffolding technique designed to enhance the functionality of language models (LMs). This approach transforms a single LM into a multi-faceted conductor, adept at managing and integrating multiple independent LM queries. By employing high-level instructions, meta-prompting guides the LM to break down complex tasks into smaller, more manageable subtasks. These subtasks are then handled by distinct "expert" instances of the same LM, each operating under specific, tailored instructions. Central to this process is the LM itself, in its role as the conductor, which ensures seamless communication and effective integration of the outputs from these expert models. It additionally employs its inherent critical thinking and robust verification processes to refine and authenticate the end result. This collaborative prompting approach empowers a single LM to simultaneously act as a comprehensive orchestrator and a panel of diverse experts, significantly enhancing its performance across a wide array of tasks. The zero-shot, task-agnostic nature of meta-prompting greatly simplifies user interaction by obviating the need for detailed, task-specific instructions. Furthermore, our research demonstrates the seamless integration of external tools, such as a Python interpreter, into the meta-prompting framework, thereby broadening its applicability and utility. Through rigorous experimentation with GPT-4, we establish the superiority of meta-prompting over conventional scaffolding methods: When averaged across all tasks, including the Game of 24, Checkmate-in-One, and Python Programming Puzzles, meta-prompting, augmented with a Python interpreter functionality, surpasses standard prompting by 17.1%, expert (dynamic) prompting by 17.3%, and multipersona prompting by 15.2%.

Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems across diverse domains. One effective paradigm for test-time scaling (TTS) involves LLM generators producing multiple solution candidates, with LLM verifiers assessing the correctness of these candidates without reference answers. In this paper, we study generative verifiers, which perform verification by generating chain-of-thought (CoT) reasoning followed by a binary verdict. We systematically analyze verification dynamics across three dimensions - problem difficulty, generator capability, and verifier generation capability - with empirical studies on 12 benchmarks across mathematical reasoning, knowledge, and natural language reasoning tasks using 14 open-source models (2B to 72B parameter range) and GPT-4o. Our experiments reveal three key findings about verification effectiveness: (1) Easy problems allow verifiers to more reliably certify correct responses; (2) Weak generators produce errors that are easier to detect than strong generators; (3) Verification ability is generally correlated with the verifier's own problem-solving capability, but this relationship varies with problem difficulty. These findings reveal opportunities to optimize basic verification strategies in TTS applications. First, given the same verifier, some weak generators can nearly match stronger ones in post-verification TTS performance (e.g., the Gemma2-9B to Gemma2-27B performance gap shrinks by 75.5%). Second, we identify cases where strong verifiers offer limited advantage over weak ones, as both fail to provide meaningful verification gains, suggesting that verifier scaling alone cannot overcome fundamental verification challenges.

Large Language Models (LLMs) like ChatGPT demonstrate significant potential in the medical field, often evaluated using multiple-choice questions (MCQs) similar to those found on the USMLE. Despite their prevalence in medical education, MCQs have limitations that might be exacerbated when assessing LLMs. To evaluate the effectiveness of MCQs in assessing the performance of LLMs, we developed a fictional medical benchmark focused on a non-existent gland, the Glianorex. This approach allowed us to isolate the knowledge of the LLM from its test-taking abilities. We used GPT-4 to generate a comprehensive textbook on the Glianorex in both English and French and developed corresponding multiple-choice questions in both languages. We evaluated various open-source, proprietary, and domain-specific LLMs using these questions in a zero-shot setting. The models achieved average scores around 67%, with minor performance differences between larger and smaller models. Performance was slightly higher in English than in French. Fine-tuned medical models showed some improvement over their base versions in English but not in French. The uniformly high performance across models suggests that traditional MCQ-based benchmarks may not accurately measure LLMs' clinical knowledge and reasoning abilities, instead highlighting their pattern recognition skills. This study underscores the need for more robust evaluation methods to better assess the true capabilities of LLMs in medical contexts.

In this paper, we propose the task of consecutive question generation (CQG), which generates a set of logically related question-answer pairs to understand a whole passage, with a comprehensive consideration of the aspects including accuracy, coverage, and informativeness. To achieve this, we first examine the four key elements of CQG, i.e., question, answer, rationale, and context history, and propose a novel dynamic multitask framework with one main task generating a question-answer pair, and four auxiliary tasks generating other elements. It directly helps the model generate good questions through both joint training and self-reranking. At the same time, to fully explore the worth-asking information in a given passage, we make use of the reranking losses to sample the rationales and search for the best question series globally. Finally, we measure our strategy by QA data augmentation and manual evaluation, as well as a novel application of generated question-answer pairs on DocNLI. We prove that our strategy can improve question generation significantly and benefit multiple related NLP tasks.

This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data collection pipeline leveraging advanced foundation models, namely GPT-4V and DALL-E 3. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs featuring input and output images with detailed text prompts, followed by precise alignment ensured through post-processing. In addition, we propose two evaluation metrics, Alignment and Coherence, to quantitatively assess the quality of image edit pairs using GPT-4V. HQ-Edits high-resolution images, rich in detail and accompanied by comprehensive editing prompts, substantially enhance the capabilities of existing image editing models. For example, an HQ-Edit finetuned InstructPix2Pix can attain state-of-the-art image editing performance, even surpassing those models fine-tuned with human-annotated data. The project page is https://thefllood.github.io/HQEdit_web.

Large vision-language models (LVLMs) are ignorant of the up-to-date knowledge, such as LLaVA series, because they cannot be updated frequently due to the large amount of resources required, and therefore fail in many cases. For example, if a LVLM was released on January 2024, and it wouldn't know the detailed plot of the new movie Dune 2, which wasn't released until February 2024. To solve the problem, a promising solution is to provide LVLMs with up-to-date knowledge via internet search during inference, i.e., internet-augmented generation (IAG), which is already integrated in some closed-source commercial LVLMs such as GPT-4V. However, the specific mechanics underpinning them remain a mystery. In this paper, we propose a plug-and-play framework, for augmenting existing LVLMs in handling visual question answering (VQA) about up-to-date knowledge, dubbed UDKAG. A hierarchical filtering model is trained to effectively and efficiently find the most helpful content from the websites returned by a search engine to prompt LVLMs with up-to-date knowledge. To train the model and evaluate our framework's performance, we propose a pipeline to automatically generate news-related VQA samples to construct a dataset, dubbed UDK-VQA. A multi-model voting mechanism is introduced to label the usefulness of website/content for VQA samples to construct the training set. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4V by about 25% in accuracy.

In machine learning, generalization against distribution shifts -- where deployment conditions diverge from the training scenarios -- is crucial, particularly in fields like climate modeling, biomedicine, and autonomous driving. The emergence of foundation models, distinguished by their extensive pretraining and task versatility, has led to an increased interest in their adaptability to distribution shifts. GPT-4V(ision) acts as the most advanced publicly accessible multimodal foundation model, with extensive applications across various domains, including anomaly detection, video understanding, image generation, and medical diagnosis. However, its robustness against data distributions remains largely underexplored. Addressing this gap, this study rigorously evaluates GPT-4V's adaptability and generalization capabilities in dynamic environments, benchmarking against prominent models like CLIP and LLaVA. We delve into GPT-4V's zero-shot generalization across 13 diverse datasets spanning natural, medical, and molecular domains. We further investigate its adaptability to controlled data perturbations and examine the efficacy of in-context learning as a tool to enhance its adaptation. Our findings delineate GPT-4V's capability boundaries in distribution shifts, shedding light on its strengths and limitations across various scenarios. Importantly, this investigation contributes to our understanding of how AI foundation models generalize to distribution shifts, offering pivotal insights into their adaptability and robustness. Code is publicly available at https://github.com/jameszhou-gl/gpt-4v-distribution-shift.

The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance. Notably, OpenCodeInterpreter-33B achieves an accuracy of 83.2 (76.4) on the average (and plus versions) of HumanEval and MBPP, closely rivaling GPT-4's 84.2 (76.2) and further elevates to 91.6 (84.6) with synthesized human feedback from GPT-4. OpenCodeInterpreter brings the gap between open-source code generation models and proprietary systems like GPT-4 Code Interpreter.

To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to the two-stage nature of the task, most studies evaluate the generation and detection separately, thereby presenting a challenge in unbiased, thorough, and applicable evaluations. In this paper, we introduce WaterBench, the first comprehensive benchmark for LLM watermarks, in which we design three crucial factors: (1) For benchmarking procedure, to ensure an apples-to-apples comparison, we first adjust each watermarking method's hyper-parameter to reach the same watermarking strength, then jointly evaluate their generation and detection performance. (2) For task selection, we diversify the input and output length to form a five-category taxonomy, covering 9 tasks. (3) For evaluation metric, we adopt the GPT4-Judge for automatically evaluating the decline of instruction-following abilities after watermarking. We evaluate 4 open-source watermarks on 2 LLMs under 2 watermarking strengths and observe the common struggles for current methods on maintaining the generation quality. The code and data are available at https://github.com/THU-KEG/WaterBench.

We present gg-bench, a collection of game environments designed to evaluate general reasoning capabilities in language models. Unlike most static benchmarks, gg-bench is a data generating process where new evaluation instances can be generated at will. In particular, gg-bench is synthetically generated by (1) using a large language model (LLM) to generate natural language descriptions of novel games, (2) using the LLM to implement each game in code as a Gym environment, and (3) training reinforcement learning (RL) agents via self-play on the generated games. We evaluate language models by their winrate against these RL agents by prompting models with the game description, current board state, and a list of valid moves, after which models output the moves they wish to take. gg-bench is challenging: state-of-the-art LLMs such as GPT-4o and Claude 3.7 Sonnet achieve winrates of 7-9% on gg-bench using in-context learning, while reasoning models such as o1, o3-mini and DeepSeek-R1 achieve average winrates of 31-36%. We release the generated games, data generation process, and evaluation code in order to support future modeling work and expansion of our benchmark.

Unit tests (UTs) play an instrumental role in assessing code correctness as well as providing feedback to a large language model (LLM) as it iteratively debugs faulty code, motivating automated test generation. However, we uncover a trade-off between generating unit test inputs that reveal errors when given a faulty code and correctly predicting the unit test output without access to the gold solution. To address this trade-off, we propose UTGen, which teaches LLMs to generate unit test inputs that reveal errors along with their correct expected outputs based on task descriptions and candidate code. We integrate UTGen into UTDebug, a robust debugging pipeline that uses generated tests to help LLMs debug effectively. Since model-generated tests can provide noisy signals (e.g., from incorrectly predicted outputs), UTDebug (i) scales UTGen via test-time compute to improve UT output prediction, and (ii) validates and back-tracks edits based on multiple generated UTs to avoid overfitting. We show that UTGen outperforms UT generation baselines by 7.59% based on a metric measuring the presence of both error-revealing UT inputs and correct UT outputs. When used with UTDebug, we find that feedback from UTGen's unit tests improves pass@1 accuracy of Qwen-2.5 7B on HumanEvalFix and our own harder debugging split of MBPP+ by over 3% and 12.35% (respectively) over other LLM-based UT generation baselines.

Nowadays, research on GUI agents is a hot topic in the AI community. However, current research focuses on GUI task automation, limiting the scope of applications in various GUI scenarios. In this paper, we propose a formalized and comprehensive environment to evaluate the entire process of automated GUI Testing (GTArena), offering a fair, standardized environment for consistent operation of diverse multimodal large language models. We divide the testing process into three key subtasks: test intention generation, test task execution, and GUI defect detection, and construct a benchmark dataset based on these to conduct a comprehensive evaluation. It evaluates the performance of different models using three data types: real mobile applications, mobile applications with artificially injected defects, and synthetic data, thoroughly assessing their capabilities in this relevant task. Additionally, we propose a method that helps researchers explore the correlation between the performance of multimodal language large models in specific scenarios and their general capabilities in standard benchmark tests. Experimental results indicate that even the most advanced models struggle to perform well across all sub-tasks of automated GUI Testing, highlighting a significant gap between the current capabilities of Autonomous GUI Testing and its practical, real-world applicability. This gap provides guidance for the future direction of GUI Agent development. Our code is available at https://github.com/ZJU-ACES-ISE/ChatUITest.

Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain. In particular, we consider PDDL domains and use GPT-4 to synthesize Python programs. We also consider (1) Chain-of-Thought (CoT) summarization, where the LLM is prompted to summarize the domain and propose a strategy in words before synthesizing the program; and (2) automated debugging, where the program is validated with respect to the training tasks, and in case of errors, the LLM is re-prompted with four types of feedback. We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. Overall, we find that GPT-4 is a surprisingly powerful generalized planner. We also conclude that automated debugging is very important, that CoT summarization has non-uniform impact, that GPT-4 is far superior to GPT-3.5, and that just two training tasks are often sufficient for strong generalization.

This paper presents a critical examination of current approaches to replicating OpenAI's O1 model capabilities, with particular focus on the widespread but often undisclosed use of knowledge distillation techniques. While our previous work explored the fundamental technical path to O1 replication, this study reveals how simple distillation from O1's API, combined with supervised fine-tuning, can achieve superior performance on complex mathematical reasoning tasks. Through extensive experiments, we show that a base model fine-tuned on simply tens of thousands of samples O1-distilled long-thought chains outperforms O1-preview on the American Invitational Mathematics Examination (AIME) with minimal technical complexity. Moreover, our investigation extends beyond mathematical reasoning to explore the generalization capabilities of O1-distilled models across diverse tasks: hallucination, safety and open-domain QA. Notably, despite training only on mathematical problem-solving data, our models demonstrated strong generalization to open-ended QA tasks and became significantly less susceptible to sycophancy after fine-tuning. We deliberately make this finding public to promote transparency in AI research and to challenge the current trend of obscured technical claims in the field. Our work includes: (1) A detailed technical exposition of the distillation process and its effectiveness, (2) A comprehensive benchmark framework for evaluating and categorizing O1 replication attempts based on their technical transparency and reproducibility, (3) A critical discussion of the limitations and potential risks of over-relying on distillation approaches, our analysis culminates in a crucial bitter lesson: while the pursuit of more capable AI systems is important, the development of researchers grounded in first-principles thinking is paramount.

Laboratory accidents pose significant risks to human life and property, underscoring the importance of robust safety protocols. Despite advancements in safety training, laboratory personnel may still unknowingly engage in unsafe practices. With the increasing reliance on large language models (LLMs) for guidance in various fields, including laboratory settings, there is a growing concern about their reliability in critical safety-related decision-making. Unlike trained human researchers, LLMs lack formal lab safety education, raising questions about their ability to provide safe and accurate guidance. Existing research on LLM trustworthiness primarily focuses on issues such as ethical compliance, truthfulness, and fairness but fails to fully cover safety-critical real-world applications, like lab safety. To address this gap, we propose the Laboratory Safety Benchmark (LabSafety Bench), a comprehensive evaluation framework based on a new taxonomy aligned with Occupational Safety and Health Administration (OSHA) protocols. This benchmark includes 765 multiple-choice questions verified by human experts, assessing LLMs and vision language models (VLMs) performance in lab safety contexts. Our evaluations demonstrate that while GPT-4o outperforms human participants, it is still prone to critical errors, highlighting the risks of relying on LLMs in safety-critical environments. Our findings emphasize the need for specialized benchmarks to accurately assess the trustworthiness of LLMs in real-world safety applications.

Large language models have shown promising performance in code generation benchmarks. However, a considerable divide exists between these benchmark achievements and their practical applicability, primarily attributed to real-world programming's reliance on pre-existing libraries. Instead of evaluating LLMs to code from scratch, this work aims to propose a new evaluation setup where LLMs use open-source libraries to finish machine learning tasks. Therefore, we propose ML-Bench, an expansive benchmark developed to assess the effectiveness of LLMs in leveraging existing functions in open-source libraries. Consisting of 10044 samples spanning 130 tasks over 14 notable machine learning GitHub repositories. In this setting, given a specific machine learning task instruction and the accompanying README in a codebase, an LLM is tasked to generate code to accomplish the task. This necessitates the comprehension of long and language-code interleaved documents, as well as the understanding of complex cross-file code structures, introducing new challenges. Notably, while GPT-4 exhibits remarkable improvement over other LLMs, it manages to accomplish only 39.73\% of the tasks, leaving a huge space for improvement. We address these challenges by proposing ML-Agent, designed to effectively navigate the codebase, locate documentation, retrieve code, and generate executable code. Empirical results demonstrate that ML-Agent, built upon GPT-4, results in further improvements. Code, data, and models are available at https://ml-bench.github.io/.

This paper introduces Patched MOA (Mixture of Agents), an inference optimization technique that significantly enhances the performance of large language models (LLMs) across diverse software development tasks. We evaluate three inference optimization algorithms - Best of N, Mixture of Agents, and Monte Carlo Tree Search and demonstrate that Patched MOA can boost the performance of smaller models to surpass that of larger, more expensive models. Notably, our approach improves the gpt-4o-mini model's performance on the Arena-Hard-Auto benchmark by 15.52%, outperforming gpt-4-turbo at a fraction of the cost. We also apply Patched MOA to various software development workflows, showing consistent improvements in task completion rates. Our method is model-agnostic, transparent to end-users, and can be easily integrated into existing LLM pipelines. This work contributes to the growing field of LLM optimization, offering a cost-effective solution for enhancing model performance without the need for fine-tuning or larger models.

Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to address diverse real-world challenges. Assessing the capability of LLMs to utilise tools necessitates large-scale and stable benchmarks. However, previous works relied on either hand-crafted online tools with limited scale, or large-scale real online APIs suffering from instability of API status. To address this problem, we introduce StableToolBench, a benchmark evolving from ToolBench, proposing a virtual API server and stable evaluation system. The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status. Meanwhile, the stable evaluation system designs solvable pass and win rates using GPT-4 as the automatic evaluator to eliminate the randomness during evaluation. Experimental results demonstrate the stability of StableToolBench, and further discuss the effectiveness of API simulators, the caching system, and the evaluator system.

Test-time scaling (TTS) has proven effective in enhancing the reasoning capabilities of large language models (LLMs). Verification plays a key role in TTS, simultaneously influencing (1) reasoning performance and (2) compute efficiency, due to the quality and computational cost of verification. In this work, we challenge the conventional paradigms of verification, and make the first attempt toward systematically investigating the impact of verification granularity-that is, how frequently the verifier is invoked during generation, beyond verifying only the final output or individual generation steps. To this end, we introduce Variable Granularity Search (VG-Search), a unified algorithm that generalizes beam search and Best-of-N sampling via a tunable granularity parameter g. Extensive experiments with VG-Search under varying compute budgets, generator-verifier configurations, and task attributes reveal that dynamically selecting g can improve the compute efficiency and scaling behavior. Building on these findings, we propose adaptive VG-Search strategies that achieve accuracy gains of up to 3.1\% over Beam Search and 3.6\% over Best-of-N, while reducing FLOPs by over 52\%. We will open-source the code to support future research.

Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct this dataset by leveraging the versatile capabilities of GPT-4o to unify and refine three popular image-editing datasets: OmniEdit, HQ-Edit, and UltraEdit. Specifically, our methodology involves 1) regenerating output images to enhance visual quality and instruction alignment, and 2) selectively rewriting prompts to improve semantic clarity. To validate the efficacy of our dataset, we fine-tune advanced open-source models on GPT-IMAGE-EDIT-1.5M. The empirical results are exciting, e.g., the fine-tuned FluxKontext achieves highly competitive performance across a comprehensive suite of benchmarks, including 7.24 on GEdit-EN, 3.80 on ImgEdit-Full, and 8.78 on Complex-Edit, showing stronger instruction following and higher perceptual quality while maintaining identity. These scores markedly exceed all previously published open-source methods and substantially narrow the gap to leading proprietary models. We hope the full release of GPT-IMAGE-EDIT-1.5M can help to catalyze further open research in instruction-guided image editing.

When unsure about an answer, humans often respond with more words than necessary, hoping that part of the response will be correct. We observe a similar behavior in large language models (LLMs), which we term "Verbosity Compensation" (VC). VC is harmful because it confuses the user understanding, leading to low efficiency, and influences the LLM services by increasing the latency and cost of generating useless tokens. In this paper, we present the first work that defines and analyzes Verbosity Compensation, explores its causes, and proposes a simple mitigating approach. We define Verbosity Compensation as the behavior of generating responses that can be compressed without information loss when prompted to write concisely. Our experiments, conducted on five datasets of knowledge and reasoning-based QA tasks with 14 newly developed LLMs, reveal three conclusions. 1) We reveal a pervasive presence of verbosity compensation across all models and all datasets. Notably, GPT-4 exhibits a VC frequency of 50.40%. 2) We reveal the large performance gap between verbose and concise responses, with a notable difference of 27.61% on the Qasper dataset. We also demonstrate that this difference does not naturally diminish as LLM capability increases. Both 1) and 2) highlight the urgent need to mitigate the frequency of VC behavior and disentangle verbosity with veracity. We propose a simple yet effective cascade algorithm that replaces the verbose responses with the other model-generated responses. The results show that our approach effectively alleviates the VC of the Mistral model from 63.81% to 16.16% on the Qasper dataset. 3) We also find that verbose responses exhibit higher uncertainty across all five datasets, suggesting a strong connection between verbosity and model uncertainty. Our dataset and code are available at https://github.com/psunlpgroup/VerbosityLLM.

Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics can not explain their verdict or associate the scores with defects in generated text. To address this limitation, we present InstructScore, an explainable evaluation metric for text generation. By harnessing both explicit human instruction and the implicit knowledge of GPT-4, we fine-tune a text evaluation metric based on LLaMA, producing both a score for generated text and a human readable diagnostic report. We evaluate InstructScore on a variety of generation tasks, including translation, captioning, data-to-text and commonsense generation. Experiments show that our 7B model surpasses all other unsupervised metrics, including those based on 175B GPT-3 and GPT-4. Surprisingly, our InstructScore, even without direct supervision from human-rated data, achieves performance levels on par with state-of-the-art metrics like COMET22, which were fine-tuned on human ratings.

This paper provides a systematic analysis of the opportunities, challenges, and potential solutions of harnessing Large Language Models (LLMs) such as GPT-4 to dig out vulnerabilities within smart contracts based on our ongoing research. For the task of smart contract vulnerability detection, achieving practical usability hinges on identifying as many true vulnerabilities as possible while minimizing the number of false positives. Nonetheless, our empirical study reveals contradictory yet interesting findings: generating more answers with higher randomness largely boosts the likelihood of producing a correct answer but inevitably leads to a higher number of false positives. To mitigate this tension, we propose an adversarial framework dubbed GPTLens that breaks the conventional one-stage detection into two synergistic stages - generation and discrimination, for progressive detection and refinement, wherein the LLM plays dual roles, i.e., auditor and critic, respectively. The goal of auditor is to yield a broad spectrum of vulnerabilities with the hope of encompassing the correct answer, whereas the goal of critic that evaluates the validity of identified vulnerabilities is to minimize the number of false positives. Experimental results and illustrative examples demonstrate that auditor and critic work together harmoniously to yield pronounced improvements over the conventional one-stage detection. GPTLens is intuitive, strategic, and entirely LLM-driven without relying on specialist expertise in smart contracts, showcasing its methodical generality and potential to detect a broad spectrum of vulnerabilities. Our code is available at: https://github.com/git-disl/GPTLens.

Increasing test-time compute for LLMs shows promise across domains but remains underexplored in code generation, despite extensive study in math. In this paper, we propose S*, the first hybrid test-time scaling framework that substantially improves the coverage and selection accuracy of generated code. S* extends the existing parallel scaling paradigm with sequential scaling to push performance boundaries. It further leverages a novel selection mechanism that adaptively generates distinguishing inputs for pairwise comparison, combined with execution-grounded information to robustly identify correct solutions. We evaluate across 12 Large Language Models and Large Reasoning Model and show: (1) S* consistently improves performance across model families and sizes, enabling a 3B model to outperform GPT-4o-mini; (2) S* enables non-reasoning models to surpass reasoning models - GPT-4o-mini with S* outperforms o1-preview by 3.7% on LiveCodeBench; (3) S* further boosts state-of-the-art reasoning models - DeepSeek-R1-Distill-Qwen-32B with S* achieves 85.7% on LiveCodeBench, approaching o1 (high) at 88.5%. Code will be available under https://github.com/NovaSky-AI/SkyThought.

There have been widespread claims about Large Language Models (LLMs) being able to successfully verify or self-critique their candidate solutions in reasoning problems in an iterative mode. Intrigued by those claims, in this paper we set out to investigate the verification/self-critiquing abilities of large language models in the context of planning. We evaluate a planning system that employs LLMs for both plan generation and verification. We assess the verifier LLM's performance against ground-truth verification, the impact of self-critiquing on plan generation, and the influence of varying feedback levels on system performance. Using GPT-4, a state-of-the-art LLM, for both generation and verification, our findings reveal that self-critiquing appears to diminish plan generation performance, especially when compared to systems with external, sound verifiers and the LLM verifiers in that system produce a notable number of false positives, compromising the system's reliability. Additionally, the nature of feedback, whether binary or detailed, showed minimal impact on plan generation. Collectively, our results cast doubt on the effectiveness of LLMs in a self-critiquing, iterative framework for planning tasks.

The development of robust safety benchmarks for large language models requires open, reproducible datasets that can measure both appropriate refusal of harmful content and potential over-restriction of legitimate scientific discourse. We present an open-source dataset and testing framework for evaluating LLM safety mechanisms across mainly controlled substance queries, analyzing four major models' responses to systematically varied prompts. Our results reveal distinct safety profiles: Claude-3.5-sonnet demonstrated the most conservative approach with 73% refusals and 27% allowances, while Mistral attempted to answer 100% of queries. GPT-3.5-turbo showed moderate restriction with 10% refusals and 90% allowances, and Grok-2 registered 20% refusals and 80% allowances. Testing prompt variation strategies revealed decreasing response consistency, from 85% with single prompts to 65% with five variations. This publicly available benchmark enables systematic evaluation of the critical balance between necessary safety restrictions and potential over-censorship of legitimate scientific inquiry, while providing a foundation for measuring progress in AI safety implementation. Chain-of-thought analysis reveals potential vulnerabilities in safety mechanisms, highlighting the complexity of implementing robust safeguards without unduly restricting desirable and valid scientific discourse.

Legal professionals need to write analyses that rely on citations to relevant precedents, i.e., previous case decisions. Intelligent systems assisting legal professionals in writing such documents provide great benefits but are challenging to design. Such systems need to help locate, summarize, and reason over salient precedents in order to be useful. To enable systems for such tasks, we work with legal professionals to transform a large open-source legal corpus into a dataset supporting two important backbone tasks: information retrieval (IR) and retrieval-augmented generation (RAG). This dataset CLERC (Case Law Evaluation Retrieval Corpus), is constructed for training and evaluating models on their ability to (1) find corresponding citations for a given piece of legal analysis and to (2) compile the text of these citations (as well as previous context) into a cogent analysis that supports a reasoning goal. We benchmark state-of-the-art models on CLERC, showing that current approaches still struggle: GPT-4o generates analyses with the highest ROUGE F-scores but hallucinates the most, while zero-shot IR models only achieve 48.3% recall@1000.

Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e.g., extractive, abstractive), require different model architectures (e.g., generative, discriminative), and setups (e.g., with or without retrieval). Despite having a large number of powerful, specialized QA pipelines (which we refer to as Skills) that consider a single domain, model or setup, there exists no framework where users can easily explore and compare such pipelines and can extend them according to their needs. To address this issue, we present UKP-SQUARE, an extensible online QA platform for researchers which allows users to query and analyze a large collection of modern Skills via a user-friendly web interface and integrated behavioural tests. In addition, QA researchers can develop, manage, and share their custom Skills using our microservices that support a wide range of models (Transformers, Adapters, ONNX), datastores and retrieval techniques (e.g., sparse and dense). UKP-SQUARE is available on https://square.ukp-lab.de.

We introduce MacroBench, a code-first benchmark that evaluates whether LLMs can synthesize reusable browser-automation programs (macros) from natural-language goals by reading HTML/DOM and emitting Selenium. MacroBench instantiates seven self-hosted sites covering 681 tasks across interaction complexity and targeting difficulty. Our end-to-end protocol validates generated code via static checks, sandboxed execution, and outcome verification (DOM assertions, database snapshots), and includes a safety suite for scraping, spam/abuse, and credential/privacy prompts. Across 2,636 model-task runs, we observe stratified success: GPT-4o-mini (96.8%), GPT-4o (95.3%), Gemini (89.0%), DeepSeek (83.4%). Models handle simple tasks reliably (91.7%) but fail on complex workflows (0.0%), and none meet production-quality coding practices despite functional completion. We release our complete benchmark pipeline, evaluation framework, and experimental results at https://github.com/hyunjun1121/MacroBench to enable reproducible assessment of macro synthesis for web automation.

Recent advances in Text-to-3D (T23D) generative models have enabled the synthesis of diverse, high-fidelity 3D assets from textual prompts. However, existing challenges restrict the development of reliable T23D quality assessment (T23DQA). First, existing benchmarks are outdated, fragmented, and coarse-grained, making fine-grained metric training infeasible. Moreover, current objective metrics exhibit inherent design limitations, resulting in non-representative feature extraction and diminished metric robustness. To address these limitations, we introduce T23D-CompBench, a comprehensive benchmark for compositional T23D generation. We define five components with twelve sub-components for compositional prompts, which are used to generate 3,600 textured meshes from ten state-of-the-art generative models. A large-scale subjective experiment is conducted to collect 129,600 reliable human ratings across different perspectives. Based on T23D-CompBench, we further propose Rank2Score, an effective evaluator with two-stage training for T23DQA. Rank2Score enhances pairwise training via supervised contrastive regression and curriculum learning in the first stage, and subsequently refines predictions using mean opinion scores to achieve closer alignment with human judgments in the second stage. Extensive experiments and downstream applications demonstrate that Rank2Score consistently outperforms existing metrics across multiple dimensions and can additionally serve as a reward function to optimize generative models. The project is available at https://cbysjtu.github.io/Rank2Score/.

In August 2025, OpenAI released GPT-OSS models, its first open weight large language models since GPT-2 in 2019, comprising two mixture of experts architectures with 120B and 20B parameters. We evaluated both variants against six contemporary open source large language models ranging from 14.7B to 235B parameters, representing both dense and sparse designs, across ten benchmarks covering general knowledge, mathematical reasoning, code generation, multilingual understanding, and conversational ability. All models were tested in unquantised form under standardised inference settings, with statistical validation using McNemars test and effect size analysis. Results show that gpt-oss-20B consistently outperforms gpt-oss-120B on several benchmarks, such as HumanEval and MMLU, despite requiring substantially less memory and energy per response. Both models demonstrate mid-tier overall performance within the current open source landscape, with relative strength in code generation and notable weaknesses in multilingual tasks. These findings provide empirical evidence that scaling in sparse architectures may not yield proportional performance gains, underscoring the need for further investigation into optimisation strategies and informing more efficient model selection for future open source deployments.

Open-domain Question Answering models which directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared to conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models lack the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate improved QA-pair models, we introduce Probably Asked Questions (PAQ), a very large resource of 65M automatically-generated QA-pairs. We introduce a new QA-pair retriever, RePAQ, to complement PAQ. We find that PAQ preempts and caches test questions, enabling RePAQ to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. Using PAQ, we train CBQA models which outperform comparable baselines by 5%, but trail RePAQ by over 15%, indicating the effectiveness of explicit retrieval. RePAQ can be configured for size (under 500MB) or speed (over 1K questions per second) whilst retaining high accuracy. Lastly, we demonstrate RePAQ's strength at selective QA, abstaining from answering when it is likely to be incorrect. This enables RePAQ to ``back-off" to a more expensive state-of-the-art model, leading to a combined system which is both more accurate and 2x faster than the state-of-the-art model alone.

GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities. However, despite the abundance of research on the difference in capabilities between GPT series models and fine-tuned models, there has been limited attention given to the evolution of GPT series models' capabilities over time. To conduct a comprehensive analysis of the capabilities of GPT series models, we select six representative models, comprising two GPT-3 series models (i.e., davinci and text-davinci-001) and four GPT-3.5 series models (i.e., code-davinci-002, text-davinci-002, text-davinci-003, and gpt-3.5-turbo). We evaluate their performance on nine natural language understanding (NLU) tasks using 21 datasets. In particular, we compare the performance and robustness of different models for each task under zero-shot and few-shot scenarios. Our extensive experiments reveal that the overall ability of GPT series models on NLU tasks does not increase gradually as the models evolve, especially with the introduction of the RLHF training strategy. While this strategy enhances the models' ability to generate human-like responses, it also compromises their ability to solve some tasks. Furthermore, our findings indicate that there is still room for improvement in areas such as model robustness.

In recent years, automated radiology report generation has experienced significant growth. This paper introduces MRScore, an automatic evaluation metric tailored for radiology report generation by leveraging Large Language Models (LLMs). Conventional NLG (natural language generation) metrics like BLEU are inadequate for accurately assessing the generated radiology reports, as systematically demonstrated by our observations within this paper. To address this challenge, we collaborated with radiologists to develop a framework that guides LLMs for radiology report evaluation, ensuring alignment with human analysis. Our framework includes two key components: i) utilizing GPT to generate large amounts of training data, i.e., reports with different qualities, and ii) pairing GPT-generated reports as accepted and rejected samples and training LLMs to produce MRScore as the model reward. Our experiments demonstrate MRScore's higher correlation with human judgments and superior performance in model selection compared to traditional metrics. Our code and datasets will be available on GitHub.

Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder based similarity metrics transfer well for QA evaluation, but they are limited by the usage of a single correct reference answer. We propose a new evaluation metric: SQuArE (Sentence-level QUestion AnsweRing Evaluation), using multiple reference answers (combining multiple correct and incorrect references) for sentence-form QA. We evaluate SQuArE on both sentence-level extractive (Answer Selection) and generative (GenQA) QA systems, across multiple academic and industrial datasets, and show that it outperforms previous baselines and obtains the highest correlation with human annotations.

Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decoding with rule-based automata or fine-tuning with manually crafted format instructions, both of which struggle with open-domain format requirements. To address this limitation, we introduce a novel framework for controlled generation in LLMs, leveraging user-provided, one-shot QA pairs. This study investigates LLMs' capabilities to follow open-domain, one-shot constraints and replicate the format of the example answers. We observe that this is a non-trivial problem for current LLMs. We also develop a dataset collection methodology for supervised fine-tuning that enhances the open-domain format control of LLMs without degrading output quality, as well as a benchmark on which we evaluate both the helpfulness and format correctness of LLM outputs. The resulting datasets, named OIFC-SFT, along with the related code, will be made publicly available at https://github.com/cofe-ai/OIFC.

Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection. They significantly outperform the best fast-thinking models, such as GPT-4o, on various math and science benchmarks. However, their multimodal reasoning capabilities remain on par with fast-thinking models. For instance, GPT-o1's performance on benchmarks like MathVista, MathVerse, and MathVision is similar to fast-thinking models. In this paper, we aim to enhance the slow-thinking capabilities of vision-language models using reinforcement learning (without relying on distillation) to advance the state of the art. First, we adapt the GRPO algorithm with a novel technique called Selective Sample Replay (SSR) to address the vanishing advantages problem. While this approach yields strong performance, the resulting RL-trained models exhibit limited self-reflection or self-verification. To further encourage slow-thinking, we introduce Forced Rethinking, which appends a textual rethinking trigger to the end of initial rollouts in RL training, explicitly enforcing a self-reflection reasoning step. By combining these two techniques, our model, VL-Rethinker, advances state-of-the-art scores on MathVista, MathVerse, and MathVision to achieve 80.3%, 61.8%, and 43.9% respectively. VL-Rethinker also achieves open-source SoTA on multi-disciplinary benchmarks such as MMMU-Pro, EMMA, and MEGA-Bench, narrowing the gap with GPT-o1.

Recent advancements in language models have showcased human-comparable performance in academic entrance exams. However, existing studies often overlook questions that require the integration of visual comprehension, thus compromising the full spectrum and complexity inherent in real-world scenarios. To address this gap, we present a comprehensive framework to evaluate language models on entrance exams, which incorporates both textual and visual elements. We evaluate the two most recent editions of Exame Nacional do Ensino M\'edio (ENEM), the main standardized entrance examination adopted by Brazilian universities. Our study not only reaffirms the capabilities of GPT-4 as the state of the art for handling complex multidisciplinary questions, but also pioneers in offering a realistic assessment of multimodal language models on Portuguese examinations. One of the highlights is that text captions transcribing visual content outperform the direct use of images, suggesting that the vision model has room for improvement. Yet, despite improvements afforded by images or captions, mathematical questions remain a challenge for these state-of-the-art models. The code and data used on experiments are available at https://github.com/piresramon/gpt-4-enem.

The recently released Google Gemini class of models are the first to comprehensively report results that rival the OpenAI GPT series across a wide variety of tasks. In this paper, we do an in-depth exploration of Gemini's language abilities, making two contributions. First, we provide a third-party, objective comparison of the abilities of the OpenAI GPT and Google Gemini models with reproducible code and fully transparent results. Second, we take a closer look at the results, identifying areas where one of the two model classes excels. We perform this analysis over 10 datasets testing a variety of language abilities, including reasoning, answering knowledge-based questions, solving math problems, translating between languages, generating code, and acting as instruction-following agents. From this analysis, we find that Gemini Pro achieves accuracy that is close but slightly inferior to the corresponding GPT 3.5 Turbo on all tasks that we benchmarked. We further provide explanations for some of this under-performance, including failures in mathematical reasoning with many digits, sensitivity to multiple-choice answer ordering, aggressive content filtering, and others. We also identify areas where Gemini demonstrates comparably high performance, including generation into non-English languages, and handling longer and more complex reasoning chains. Code and data for reproduction can be found at https://github.com/neulab/gemini-benchmark

Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes. However, it has been increasingly challenging to evaluate the reasoning capability of LLMs. Concretely, existing outcome-based benchmarks begin to saturate and become less sufficient to monitor the progress. To this end, we present a process-based benchmark MR-BEN that demands a meta reasoning skill, where LMs are asked to locate and analyse potential errors in automatically generated reasoning steps. MR-BEN is a comprehensive benchmark comprising 5,975 questions collected from human experts, covering various subjects such as physics, chemistry, logic, coding, and more. Through our designed metrics for assessing meta-reasoning on this benchmark, we identify interesting limitations and weaknesses of current LLMs (open-source and closed-source models). For example, open-source models are seemingly comparable to GPT-4 on outcome-based benchmarks, but they lag far behind on our benchmark, revealing the underlying reasoning capability gap between them. Our dataset and codes are available on https://randolph-zeng.github.io/Mr-Ben.github.io/.

This paper proposes a novel column generation framework for combinatorial software testing. In particular, it combines Mathematical Programming and Constraint Programming in a hybrid decomposition to generate covering arrays. The approach allows generating parameterized test cases with coverage guarantees between parameter interactions of a given application. Compared to exhaustive testing, combinatorial test case generation reduces the number of tests to run significantly. Our column generation algorithm is generic and can accommodate mixed coverage arrays over heterogeneous alphabets. The algorithm is realized in practice as a cloud service and recognized as one of the five winners of the company-wide cloud application challenge at Oracle. The service is currently helping software developers from a range of different product teams in their testing efforts while exposing declarative constraint models and hybrid optimization techniques to a broader audience.

Pre-trained language models like ChatGPT have significantly improved code generation. As these models scale up, there is an increasing need for the output to handle more intricate tasks. Moreover, in bioinformatics, generating functional programs poses additional notable challenges due to the amount of domain knowledge, the need for complicated data operations, and intricate functional dependencies between the operations. Here, we present BioCoder, a benchmark developed to evaluate existing pre-trained models in generating bioinformatics code. In relation to function-code generation, BioCoder covers potential package dependencies, class declarations, and global variables. It incorporates 1026 functions and 1243 methods in Python and Java from GitHub and 253 examples from the Rosalind Project. BioCoder incorporates a fuzz-testing framework for evaluation, and we have applied it to evaluate many models including InCoder, CodeGen, CodeGen2, SantaCoder, StarCoder, StarCoder+, InstructCodeT5+, and ChatGPT. Our detailed analysis of these models emphasizes the importance of domain knowledge, pragmatic code generation, and contextual understanding. Our dataset, benchmark, Docker images, and scripts required for testing are all available at https://github.com/gersteinlab/biocoder.

Run-time steering strategies like Medprompt are valuable for guiding large language models (LLMs) to top performance on challenging tasks. Medprompt demonstrates that a general LLM can be focused to deliver state-of-the-art performance on specialized domains like medicine by using a prompt to elicit a run-time strategy involving chain of thought reasoning and ensembling. OpenAI's o1-preview model represents a new paradigm, where a model is designed to do run-time reasoning before generating final responses. We seek to understand the behavior of o1-preview on a diverse set of medical challenge problem benchmarks. Following on the Medprompt study with GPT-4, we systematically evaluate the o1-preview model across various medical benchmarks. Notably, even without prompting techniques, o1-preview largely outperforms the GPT-4 series with Medprompt. We further systematically study the efficacy of classic prompt engineering strategies, as represented by Medprompt, within the new paradigm of reasoning models. We found that few-shot prompting hinders o1's performance, suggesting that in-context learning may no longer be an effective steering approach for reasoning-native models. While ensembling remains viable, it is resource-intensive and requires careful cost-performance optimization. Our cost and accuracy analysis across run-time strategies reveals a Pareto frontier, with GPT-4o representing a more affordable option and o1-preview achieving state-of-the-art performance at higher cost. Although o1-preview offers top performance, GPT-4o with steering strategies like Medprompt retains value in specific contexts. Moreover, we note that the o1-preview model has reached near-saturation on many existing medical benchmarks, underscoring the need for new, challenging benchmarks. We close with reflections on general directions for inference-time computation with LLMs.

FinanceBench is a first-of-its-kind test suite for evaluating the performance of LLMs on open book financial question answering (QA). It comprises 10,231 questions about publicly traded companies, with corresponding answers and evidence strings. The questions in FinanceBench are ecologically valid and cover a diverse set of scenarios. They are intended to be clear-cut and straightforward to answer to serve as a minimum performance standard. We test 16 state of the art model configurations (including GPT-4-Turbo, Llama2 and Claude2, with vector stores and long context prompts) on a sample of 150 cases from FinanceBench, and manually review their answers (n=2,400). The cases are available open-source. We show that existing LLMs have clear limitations for financial QA. Notably, GPT-4-Turbo used with a retrieval system incorrectly answered or refused to answer 81% of questions. While augmentation techniques such as using longer context window to feed in relevant evidence improve performance, they are unrealistic for enterprise settings due to increased latency and cannot support larger financial documents. We find that all models examined exhibit weaknesses, such as hallucinations, that limit their suitability for use by enterprises.

How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evaluation. The former hurts the fairness of benchmarks, and the latter hinders practitioners from selecting superior LLMs for specific programming domains. To address these two limitations, we propose a new benchmark - EvoCodeBench, which has the following advances: (1) Evolving data. EvoCodeBench will be dynamically updated every period (e.g., 6 months) to avoid data leakage. This paper releases the first version - EvoCodeBench-2403, containing 275 samples from 25 repositories. (2) A domain taxonomy and domain labels. Based on the statistics of open-source communities, we design a programming domain taxonomy consisting of 10 popular domains. Based on the taxonomy, we annotate each sample in EvoCodeBench with a domain label. (3) Domain-specific evaluations. Besides the Pass@k, we compute the Domain-Specific Improvement (DSI) and define LLMs' comfort and strange domains. These evaluations help practitioners select superior LLMs in specific domains and discover the shortcomings of existing LLMs. We evaluate 8 popular LLMs (e.g., gpt-4, DeepSeek Coder) on EvoCodeBench and summarize some insights. EvoCodeBench reveals the actual abilities of these LLMs in real-world repositories. For example, the highest Pass@1 of gpt-4 on EvoCodeBench-2403 is only 20.74%. Besides, we evaluate LLMs in different domains and discover their comfort and strange domains. For example, gpt-4 performs best in most domains but falls behind others in the Internet domain. StarCoder 2-15B unexpectedly performs well in the Database domain and even outperforms 33B LLMs. EvoCodeBench has been released.