|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- finance |
|
|
- financial-reasoning |
|
|
- adversarial |
|
|
- critique-model |
|
|
- lora |
|
|
- safety |
|
|
- trading |
|
|
datasets: |
|
|
- wmaousley/minicrit-training-12k |
|
|
- wmaousley/finrebut-600 |
|
|
model-index: |
|
|
- name: MiniCrit-1.5B |
|
|
results: |
|
|
- task: |
|
|
type: text-classification |
|
|
name: Financial Reasoning Critique |
|
|
dataset: |
|
|
name: MiniCrit-Training-12k |
|
|
type: wmaousley/minicrit-training-12k |
|
|
metrics: |
|
|
- name: Weak Reasoning F1 |
|
|
type: f1 |
|
|
value: 0.82 |
|
|
- name: Hallucination Detection F1 |
|
|
type: f1 |
|
|
value: 0.76 |
|
|
--- |
|
|
|
|
|
# 🧠 MiniCrit-1.5B |
|
|
**Adversarial Financial Critic LLM for Trading-Rationale Evaluation** |
|
|
|
|
|
MiniCrit-1.5B is an adversarial financial-critic LLM trained to evaluate, stress-test, and rebut trading rationales produced by other LLMs. |
|
|
It serves as a **validator layer** for autonomous or semi-autonomous trading systems where hallucinated logic or weak reasoning may create financial risk. |
|
|
|
|
|
The model **does not** generate trades. |
|
|
It **only** critiques reasoning quality. |
|
|
|
|
|
--- |
|
|
|
|
|
## 📦 Model Description |
|
|
|
|
|
**Base Model:** 1.5B-parameter transformer |
|
|
**Tuning Method:** ATAC-LoRA |
|
|
**Training Data:** |
|
|
- **MiniCrit-Training-12k** (12,132 rationale → critique pairs) |
|
|
- **FinRebut-600** curated evaluation set |
|
|
|
|
|
**Primary Abilities** |
|
|
- Detect flawed or risky trading logic |
|
|
- Identify hallucinated financial statistics |
|
|
- Flag improper use of indicators |
|
|
- Provide adversarial rebuttals |
|
|
- Validate rationales before execution |
|
|
|
|
|
--- |
|
|
|
|
|
## 📚 Datasets |
|
|
|
|
|
### **1. MiniCrit-Training-12k** |
|
|
Large-scale dataset of institutional rationale/critique pairs. |
|
|
➡ https://huggingface.co/datasets/wmaousley/minicrit-training-12k |
|
|
|
|
|
### **2. FinRebut-600** |
|
|
Curated, high-quality adversarial rebuttal set. |
|
|
➡ https://huggingface.co/datasets/wmaousley/finrebut-600 |
|
|
|
|
|
Both datasets are available under **CC-BY-4.0**. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🚀 Intended Use |
|
|
|
|
|
### ✔ Recommended: |
|
|
- Validating LLM-generated trading rationales |
|
|
- Hallucination detection in financial explanations |
|
|
- Model-to-model critique pipelines |
|
|
- AI-safety analysis for financial agents |
|
|
- Research in adversarial financial reasoning |
|
|
|
|
|
### ❌ Not Recommended: |
|
|
- Generating trades |
|
|
- Investment decision-making |
|
|
- Fully autonomous trading without human review |
|
|
|
|
|
This model is for **research** and **evaluation** only. |
|
|
|
|
|
--- |
|
|
|
|
|
## 📈 Performance |
|
|
|
|
|
### Forward-Test (Paper Trading) |
|
|
| Metric | Value | |
|
|
|--------|-------| |
|
|
| Sharpe (baseline) | +0.20 | |
|
|
| Sharpe (MiniCrit-validated) | **+0.80** | |
|
|
| Hallucination reduction | **–48%** | |
|
|
| Weak-reasoning detection F1 | **0.82** | |
|
|
| Hallucination F1 | **0.76** | |
|
|
|
|
|
### Qualitative Strengths |
|
|
- Detects regime mismatch |
|
|
- Identifies liquidity illusions |
|
|
- Flags circular or self-justifying logic |
|
|
- Highlights data-mining |
|
|
- Generates strong evidence-demanding rebuttals |
|
|
|
|
|
--- |
|
|
|
|
|
## 🔧 Usage |
|
|
|
|
|
> This example works after the full model is uploaded to this repository. |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
model_name = "wmaousley/MiniCrit-1.5B" |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
model = AutoModelForCausalLM.from_pretrained(model_name) |
|
|
|
|
|
prompt = """Rationale: |
|
|
'NVDA is oversold so I will long because RSI is below 30.' |
|
|
|
|
|
Provide a critique. |
|
|
""" |
|
|
|
|
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
|
outputs = model.generate( |
|
|
**inputs, |
|
|
max_new_tokens=200, |
|
|
do_sample=False, |
|
|
temperature=0.0, |
|
|
) |
|
|
|
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
## 🛡️ Safety & Limitations |
|
|
|
|
|
### Model Risks |
|
|
- May produce overly forceful critiques |
|
|
- Sensitive to prompt phrasing |
|
|
- Limited deep macroeconomic understanding |
|
|
- Not a trading or financial-advice model |
|
|
|
|
|
### Mitigations |
|
|
- Does not produce trade signals |
|
|
- Outputs critique only |
|
|
- Warns about high-risk reasoning patterns |
|
|
- Datasets avoid target-label leakage |
|
|
|
|
|
--- |
|
|
|
|
|
## 📄 Citation |
|
|
|
|
|
If you use MiniCrit-1.5B, please cite: |
|
|
|
|
|
``` |
|
|
Ousley, W. A. (2025). MiniCrit-1.5B: Adversarial Financial Critic Model. |
|
|
Zenodo. https://doi.org/10.5281/zenodo.17594497 |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
## 👤 Author |
|
|
|
|
|
**William Alexander Ousley** |
|
|
AI/ML Researcher — Autonomous Trading Systems |
|
|
ORCID: https://orcid.org/0009-0009-2503-2010 |
|
|
|
|
|
--- |
|
|
|
|
|
## 🤝 Contributions |
|
|
|
|
|
Pull requests welcome. |
|
|
|
|
|
Ideal contributions include: |
|
|
- Dataset expansions |
|
|
- Adversarial-evaluation benchmarks |
|
|
- Safety improvements |
|
|
- ATAC-LoRA optimization |
|
|
- Forward-test research |
|
|
|
|
|
--- |
|
|
|
|
|
## 📬 Contact |
|
|
|
|
|
📧 Email: **[email protected]** |
|
|
🔗 GitHub: https://github.com/wmaousley |
|
|
|
