Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Hongzheng, Chen, Yongqiang, Qin, Zeyu, Liu, Tongliang, Xiao, Chaowei, Zhang, Kun, Han, Bo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2505.18672