Label Smoothing Improves Gradient Ascent in LLM Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pang, Zirui, Zheng, Hao, Deng, Zhijie, Li, Ling, Zhong, Zixin, Wei, Jiaheng
Format:	Preprint
Published:	2025
Subjects:	Machine Learning 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/2510.22376