Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Si, Jianfeng, Sun, Lin, Tan, Zhewen, Zhang, Xiangzheng
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/2508.14904