Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2412.13862
Cited By
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
18 December 2024
Yuzhong Hong
Hanshan Zhang
Junwei Bao
Hongfei Jiang
Yang Song
OffRL
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model"
1 / 1 papers shown
Title
Energy-Based Reward Models for Robust Language Model Alignment
Anamika Lochab
Ruqi Zhang
46
0
0
17 Apr 2025
1