Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Royer, Corentin, Bhattacharjya, Debarun, Rossiello, Gaetano, Giovannini, Andrea, El-Assady, Mennatallah
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/2603.17815