Skip to content

Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models.

Chenglong Wang, Yifu Huo, Yang Gan, Yongyu Mu, Qiaozhi He, Murun Yang, Bei Li, Chunliang Zhang, Tongran Liu, Anxiang Ma, Zhengtao Yu, Jingbo Zhu, Tong Xiao

VenueA*AAAI
Year2026
ProceedingsAAAI

Browse the full AAAI paper archive.