Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Leong, Chak Tou, Yin, Qingyu, Wang, Jian, Li, Wenjie
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.13946