Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rachmil, Oren, Shapira, Avishag, Betser, Roy, Gershon, Itay, Hofman, Omer, Shabtai, Asaf, Elovici, Yuval, Vainshtein, Roman
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/2512.03994