Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Guozhi, Lin, Weiwei, Huang, Tiansheng, Mo, Ruichao, Mu, Qi, Wang, Xiumin, Shen, Li
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.05228