Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Liang, Han, Xueting, Shen, Li, Bai, Jing, Wong, Kam-Fai
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/2506.03850