3 papers
cs.LG2024
Correcting Large Language Model Behavior via Influence Function
Han Zhang, Zhuo Zhang, Yi Zhang +8
Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences. However, the dynamic nature…
cs.LG2024
Online Self-Preferring Language Models
Yuanzhao Zhai, Zhuo Zhang, Kele Xu +6
Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward…
cs.LG2024
COPR: Continual Human Preference Learning via Optimal Policy Regularization
Han Zhang, Lin Gui, Yu Lei +8
Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences. Given the evolving nature of…