Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
Xinpeng Wang
,
Chengzhi Hu
,
Paul Röttger
,
Barbara Plank
Published: 01 Jan 2025, Last Modified: 14 May 2025
ICLR 2025
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Loading