LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Guanghao, Qiu, Panjia, Chen, Cen, Li, Hongyu, Chu, Mingyuan, Zhang, Xin, Zhou, Jun
Format:	Preprint
Published:	2026
Subjects:	Computers and Society Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.00038