"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mei, Lingrui, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Mao, Jiayi, Cheng, Xueqi
Format:	Preprint
Published:	2024
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/2406.11668