LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Abdelhalim, Alhassan, Edinger, Janick, Laue, Sören, Regneri, Michaela
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.22928