Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nie, Shuo, Deng, Hexuan, Wang, Chao, Fang, Ruiyu, Liu, Xuebo, Song, Shuangyong, Li, Yu, Zhang, Min, Li, Xuelong
Format:	Preprint
Published:	2026
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/2602.05897