Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Shuxun, Yin, Qingyu, Leong, Chak Tou, Zhang, Qiang, Yang, Linyi
Format:	Preprint
Published:	2025
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/2505.13514