Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ren-Jian, Xue, Ke, Qin, Zeyu, Li, Ziniu, Tang, Sheng, Li, Hao-Tian, Liu, Shengcai, Qian, Chao
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.07121