Skip to content

ODIN: Disentangled Reward Mitigates Hacking in RLHF.

Lichang Chen, Chen Zhu, Jiuhai Chen, Davit Soselia, Tianyi Zhou, Tom Goldstein, Heng Huang, Mohammad Shoeybi, Bryan Catanzaro

VenueA*ICML
Year2024
ProceedingsICML

Browse the full ICML paper archive.