Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
When is RL better than DPO in RLHF? A Representation and Optimization Perspective
Ziniu Li
,
Tian Xu
,
Yang Yu
Published: 01 Jan 2024, Last Modified: 19 Jan 2025
Tiny Papers @ ICLR 2024
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Loading