Activation Dispersion Predicts LLM Factual Reliability Before It Answers

arXiv·medium signal

The Bielik study shows that a model's internal activations betray entity familiarity before it produces a single token, and that activation dispersion separates entities a model genuinely knows from those it will hallucinate about. The signal holds across model scale, offering a lightweight, inference-time hallucination-detection lever for builders deploying LLMs on knowledge-heavy tasks.