Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Luo, Yifan, Zhou, Zhennan, Wang, Meitan, Dong, Bin
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.10150