ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hardy, Amelia F., Liu, Houjun, Griffith, Allie, Lange, Bernard, Eddy, Duncan, Kochenderfer, Mykel J.
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!

Be the first to leave a comment!

Similar Items