Reward Shaping to Mitigate Reward Hacking in RLHF

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Jiayi, Zhao, Xuandong, Yao, Chengyuan, Wang, Heng, Han, Qi, Xiao, Yanghua
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence 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/2502.18770