Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Yuzhong, Zhang, Hanshan, Bao, Junwei, Jiang, Hongfei, Song, Yang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!