Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
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
Published: 01 Jan 2024, Last Modified: 13 Nov 2024
ICML 2024
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Loading