SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Maskey, Utsav, Yadav, Sumit, Dras, Mark, Naseem, Usman
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.11290