The Geometry of Ignorance: Detecting Suppressed Knowledge in LLMs through Activation Fragmentation
Evaluating whether a large language model (LLM) genuinely knows a concept remains a fundamental problem, since behavioral metrics can be fooled by suppression: a model that refuses to answer may still harbor recoverable knowledge. The framework measures the geometric coherence of \textit{anon-vectors}, the differences...
Adar Peleg, Dvir Alsheich, Tomer Ashuach et al.
· Conference on Empirical Meth... · 0 citations