Dong Yan

STAIR: Improving Safety Alignment with Introspective Reasoning

Learning LLM-as-a-Judge for Preference Alignment

3D-Properties: Identifying Challenges in DPO and Charting a Path Forward

Towards Mitigating Factual Hallucination in LLMs through Self-Alignment with Memory

Reward-Robust RLHF in LLMs

Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown

Boosting Deductive Reasoning with Step Signals In RLHF

Data-Driven Creativity: Amplifying Imagination in LLM Writing