Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pathak, Manas, Chen, Xingyao, Li, Shuozhe, Zhang, Amy, Leqi, Liu
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/2604.11996