Preference Optimization via Contrastive Divergence: Your Reward Model is Secretly an NLL Estimator

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Zhuotong, Liu, Fang, Zhu, Xuan, Qi, Yanjun, Ghavamzadeh, Mohammad
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.04567