LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ge, Yubin, Kirtane, Neeraja, Peng, Hao, Hakkani-Tür, Dilek
Format:	Preprint
Published:	2025
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/2501.14073