Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Zhanhui, Liu, Jie, Dong, Zhichen, Liu, Jiaheng, Yang, Chao, Ouyang, Wanli, Qiao, Yu
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2402.12343