Enhancing LLM Agent Safety via Causal Influence Prompting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hahm, Dongyoon, Jin, Woogyeol, Choi, June Suk, Ahn, Sungsoo, Lee, Kimin
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.00979