Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Wenbo, Liu, Zhichao, Wang, Xianlong, Yu, Haining, Jia, Xiaohua
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.01914