Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Reisizadeh, Hadi, Ruan, Jiajun, Chen, Yiwei, Pal, Soumyadeep, Liu, Sijia, Hong, Mingyi
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/2511.04934