Taming Overconfidence in LLMs: Reward Calibration in RLHF

Open Webpage

Jixuan Leng, Chengsong Huang, Banghua Zhu, Jiaxin Huang

Published: 01 Jan 2025, Last Modified: 30 Jun 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0