Evaluating Reward Model Generalization via Pairwise Maximum Discrepancy Competitions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Shunyang, Cao, Peibei, Zhu, Zhihui, Feng, Kehua, Wang, Zhihua, Ding, Keyan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.16987