6 papers
Uncertainty-Aware Reward Modeling for Stable RLHF
Licheng Pan, Haocheng Yang, Haoxuan Li +7
Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. H…
Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
Yu-An Lu, Ci-Yang Tsai, Yu-Lin Tsai +2
Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular, detailed traces can help d…
Optimal Transport for LLM Reward Modeling from Noisy Preference
Licheng Pan, Haochen Yang, Haoxuan Li +8
Reward models are fundamental to Reinforcement Learning from Human Feedback (RLHF), yet real-world datasets are inevitably corrupted by noisy preference. Conventional training obje…
Robust Reward Modeling for Large Language Models via Causal Decomposition
Yunsheng Lu, Zijiang Yang, Licheng Pan +1
Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone. Most prior work weakens thes…
A Causal Perspective for Enhancing Jailbreak Attack and Defense
Licheng Pan, Yunsheng Lu, Jiexi Liu +5
Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood.…
Large Language Models for Causal Discovery: Current Landscape and Future Directions
Guangya Wan, Yunsheng Lu, Yuqi Wu +2
Causal discovery (CD) and Large Language Models (LLMs) have emerged as transformative fields in artificial intelligence that have evolved largely independently. While CD specialize…