reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Zhaofeng, Yasunaga, Michihiro, Cohen, Andrew, Kim, Yoon, Celikyilmaz, Asli, Ghazvininejad, Marjan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.11751