Thermodynamic Diagnostics Boost LLM Hallucination Detection by 6.5 AUROC Points
The paper introduces Free‑Energy Signatures (Fes), a thermodynamic descriptor that treats each layer’s attention Laplacian as a Hamiltonian and extracts partition functions, entropy, heat capacity, and random‑matrix spectral form factors. Across six open‑weight LLMs and benchmarks, a lightweight probe using Fes outperforms previous attention‑spectral detectors, raising average AUROC by 6.5 points and achieving 0.71 in a fully unsupervised setting.