How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Wei, Ju, Guoyang, Qi, Yuanyuan
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/2603.18009