Yihong Liu

yihongLiu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 4 papers 5 months ago

Refusal Direction is Universal Across Safety-Aligned Languages

Paper • 2505.17306 • Published May 22 • 2

How Programming Concepts and Neurons Are Shared in Code Language Models

Paper • 2506.01074 • Published Jun 1 • 3

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models

Paper • 2504.04264 • Published Apr 5 • 2

Tracing Multilingual Factual Knowledge Acquisition in Pretraining

Paper • 2505.14824 • Published May 20 • 4

authored 3 papers 8 months ago

M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis

Paper • 2502.11824 • Published Feb 17 • 2

On Relation-Specific Neurons in Large Language Models

Paper • 2502.17355 • Published Feb 24 • 10

Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu

Paper • 2502.11862 • Published Feb 17

authored 6 papers about 1 year ago

LangSAMP: Language-Script Aware Multilingual Pretraining

Paper • 2409.18199 • Published Sep 26, 2024 • 1

How Transliterations Improve Crosslingual Alignment

Paper • 2409.17326 • Published Sep 25, 2024 • 1

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining

Paper • 2311.08849 • Published Nov 15, 2023 • 5

TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data

Paper • 2405.09913 • Published May 16, 2024

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment

Paper • 2406.19759 • Published Jun 28, 2024

TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models

Paper • 2401.06620 • Published Jan 12, 2024