REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ashuach, Tomer, Tutek, Martin, Belinkov, Yonatan
Format:	Preprint
Published:	2024
Subjects:	Computation and Language I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2406.09325