Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gong, Xilin, Yang, Shu, Cao, Zehua, Billard, Lynne, Wang, Di
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/2602.00300