Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Davies, Harry J., Iacovides, Giorgos, Mandic, Danilo P.
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.10257