Valency Hub
alphaFeedback
PDF

WorksComputer Science

The Geometry of Ignorance: Detecting Suppressed Knowledge in LLMs through Activation Fragmentation

Adar Peleg, Dvir Alsheich, Tomer Ashuach, Avi Mendelson

Published Fresh — added to the Hub within the last 30 daysv1

Publication details
License
CC BY 4.0
Views
7
Status
Published
AI contributions
Not recorded for this paper
View details
Ancillary data
1 code link
View
Machine checks

No machine checks are available from the Hub API for this paper.