Selective Safety Steering via Value-Filtered Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Einbinder, Bat-Sheva, Davidov, Hen, Teh, Yee Whye, Gal, Yarin, Romano, Yaniv
Format:	Preprint
Published:	2026
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/2605.14746