SOURCE-LINKED INTELLIGENCE

The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Hidden-state probes effectively detect LLM hallucinations, but the geometry of the signal remains poorly characterized, driving increasingly complex probe architectures. Across three 7B-scale models and three datasets in a paired-example paradigm, we find the signal overwhelmingly dominated by a single mean-shift component, and removing this direction collapses detection to chance. Shrinkage linear discriminant analysis closes about 73% of the gap between 1D and full-dimensional classifiers, so apparent architectural complexity largely reflects high-dimensional covariance estimation difficulty

Read original source ↗ Open in workspace

recordType

paper

region

Global