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

"Jailbreak" is a major safety concern of Large Language Models (LLMs), which occurs when malicious prompts lead LLMs to produce harmful outputs, raising issues about the reliability and safety of LLMs. Therefore, an effective evaluation of jailbreaks is very crucial to develop its mitigati...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-06
Hauptverfasser:	Lingrui Mei, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Mao, Jiayi, Cheng, Xueqi
Format:	Artikel
Sprache:	eng
Schlagworte:	Benchmarks Hallucinations Large language models
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!