3 papers
cs.CL2026
Whitening Reveals Cluster Commitment as the Geometric Separator of Hallucination Types
Matic Korun
A geometric hallucination taxonomy distinguishes three failure types -- center-drift (Type~1), wrong-well convergence (Type~2), and coverage gaps (Type~3) -- by their signatures in…
cs.CL2026
From Prerequisites to Predictions: Validating a Geometric Hallucination Taxonomy Through Controlled Induction
Matic Korun
We test whether a geometric hallucination taxonomy -- classifying failures as center-drift (Type~1), wrong-well convergence (Type~2), or coverage gaps (Type~3) -- can distinguish h…
cs.CL2026
Detecting LLM Hallucinations via Embedding Cluster Geometry: A Three-Type Taxonomy with Measurable Signatures
Matic Korun
We propose a geometric taxonomy of large language model hallucinations based on observable signatures in token embedding cluster structure. By analyzing the static embedding spaces…