Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xitao, Wang, Haijun, Wu, Jiang, Liu, Ting
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.05689