Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Shide, Li, Tianlin, Wang, Kailong, Huang, Yihao, Shi, Ling, Liu, Yang, Wang, Haoyu
Format:	Preprint
Published:	2024
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2408.15207