Yuanshun Yao

FEWL: Measuring and Mitigating LLM Hallucination Without Gold-Standard Answers

Label Smoothing Improves Machine Unlearning

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Model

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

Robust Multi-bit Text Watermark with LLM-based Paraphrasers

Learning to Watermark LLM-generated Text via Reinforcement Learning

Robust RLHF with Noisy Rewards

Progressive LLM Alignments Using Two-Player Games

Human-Instruction-Free LLM Self-Alignment with Limited Samples