Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pramanik, Vishal, Maliha, Maisha, Bastian, Nathaniel D., Jha, Sumit Kumar
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/2604.13258