Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bani-Harouni, David, Pellegrini, Chantal, Stangel, Paul, Özsoy, Ege, Zaripova, Kamilia, Navab, Nassir, Keicher, Matthias
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/2503.02623