arXiv Machine Learning June 19, 2026 By Salim Khazem

Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models

Read the original on arXiv Machine Learning →

arXiv:2606. 19404v1 Announce Type: new Abstract: Hallucination detection in large language models (LLMs) is deployment-critical, and recent work shows that the spectrum of attention-derived graph Laplacians carries strong signal about reasoning quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 11

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning

arXiv:2601. 00791v2 Announce Type: replace-cross Abstract: Verifying whether a language model is genuinely reasoning or pattern-matching remains an open problem: learned verifiers are expensive, and output-based heuristics are brittle.

By Valentin No\"el

llms rag benchmarks

arXiv Machine Learning

Jun 11

Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics

arXiv:2605. 04893v2 Announce Type: replace Abstract: When a language model processes a hallucinated response, its attention routing tends to fail in one of two shapes: over-concentrating on a narrow set of positions, or spreading so diffusely that relevance is diluted, and the shape of the failure carries diagnostic signal.

By Dominik Dahlem, Diego Maniloff, Mac Misiura

llms benchmarks

arXiv Machine Learning

Sep 17

Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models

The paper proposes using the temporal volatility of internal attention mechanisms—measured by an unsupervised attention dispersion metric—as a diagnostic signal for hallucinations in large language models. It demonstrates that spikes in attention entropy within intermediate layers correlate with reasoning breakdowns, and shows statistically significant AUC improvements of up to +0.076 over output-based baselines on GSM8K and MATH-500 benchmarks using the Qwen2.5 model family.

By Shardul P. More, Tanuja S. Pawar

llms benchmarks safety

arXiv Machine Learning

Jun 3

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs

arXiv:2606. 02628v1 Announce Type: new Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal is strongest.

By Aizierjiang Aiersilan

llms efficiency benchmarks safety

arXiv AI

Jul 28

D-Score: A Spectral Hidden-State Signal for Hallucination Detection in Large Language Models

arXiv:2607. 24586v1 Announce Type: cross Abstract: Large Language Models can produce fluent text that is false, unsupported by the available evidence, or inconsistent with information that appears to be internally represented by the model.

By Bianca Raimondi, Davide Evangelista, Maurizio Gabbrielli, Elena Loli Piccolomini

llms safety

arXiv Computer Vision

Sep 2

Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM

arXiv:2609.00231v1 Announce Type: new Abstract: Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as o...

By Peiyang Xu, Xiaopei Zhu, Jun Zhu, Xiaolin Hu

llms rag fine-tuning multimodal benchmarks safety

One email a morning, machine-written

Related stories

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning

Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics

Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs

D-Score: A Spectral Hidden-State Signal for Hallucination Detection in Large Language Models

Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM