SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Jiaqi, Chen, Chen, Hou, Chunyan, Yuan, Xiaojie
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.15594