Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Qizhou, Zhou, Jin Peng, Zhou, Zhanke, Shin, Saebyeol, Han, Bo, Weinberger, Kilian Q.
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/2502.19301