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.

Summary generated by The Flow from the publisher's feed. 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

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 AI

Aug 10

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry

arXiv:2608. 06849v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs.

By Yehan Yang, Junyuan Shang, Yang Li, Guanqun Zhao, Shuohuan Wang, Dianhai Yu

llms efficiency

arXiv Machine Learning

Jul 3

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

arXiv:2607. 01571v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by generating intermediate reasoning steps.

By Aria Masoomi, Mahsa Bazzaz, Adel Javanmard, Vahab Mirrokni

llms

Related stories

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning

Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics

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

Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness