AI RESEARCH

Whitening Reveals Cluster Commitment as the Geometric Separator of Hallucination Types

arXiv CS.CL

ArXi:2603.07755v1 Announce Type: new 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 embedding cluster space. Prior work found Types~1 and~2 indistinguishable in full-dimensional contextual measurement. We address this through PCA-whitening and eigenspectrum decomposition on GPT-2-small, using multi-run stability analysis (20 seeds) with prompt-level aggregation.