Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

Open Webpage

Juntao Dai, Taiye Chen, Yaodong Yang, Qian Zheng, Gang Pan

Published: 01 Jan 2025, Last Modified: 01 Aug 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0