Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Yu, Li, Yufei, Xiao, Wen, Liu, Cong, Dong, Yue
Format:	Preprint
Published:	2023
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2312.06924