Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhai, Naixin, Shao, Pengyang, Zheng, Binbin, Yang, Yonghui, Shen, Fei, Bai, Long, Yang, Xun
Format:	Preprint
Published:	2026
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/2601.03190