Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	An, Hao, Xu, Yang
Format:	Preprint
Published:	2025
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/2510.24020