Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Grimes, Keltin, Christiani, Marco, Shriver, David, Connor, Marissa
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.13341