Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Baixiang, Tan, Zhen, Wang, Haoran, Liu, Zijie, Li, Dawei, Payani, Ali, Liu, Huan, Chen, Tianlong, Shu, Kai
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/2506.20606