Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kulshreshtha, Devang, Su, Hang, Jin, Haibo, Hegde, Chinmay, Wang, Haohan
Format:	Preprint
Published:	2026
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/2601.02670