Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
Audrey Huang
,
Wenhao Zhan
,
Tengyang Xie
,
Jason D. Lee
,
Wen Sun
,
Akshay Krishnamurthy
,
Dylan J. Foster
Published: 01 Jan 2025, Last Modified: 01 Oct 2025
ICLR 2025
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Loading