注意力分散作为大型语言模型幻觉的诊断信号

Computer Science > Computation and Language arXiv:2609.18320 (cs) [Submitted on 16 Sep 2026] Title:Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models Authors:Shardul P. More, Tanuja S. Pawar View a PDF of the paper titled Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models, by Shardul P. More and 1 other authors View PDF HTML (experimental) Abstract:Large Language Models (LLMs) frequently exhibit hallucinations, presenting a major barrier to reliability in complex reasoning tasks. While traditional detection methods rely on output-based confidence metrics, these logits are often miscalibrated by modern alignment techniques. In this paper, we investigate the temporal volatility of internal attention mechanisms as an alternative diagnostic signal for hallucination that does not depend on output calibration. By introducing an unsupervised metric for attention dispersion, we show that epistemic uncertainty leaves a measurable trace within intermediate layers, where spikes in attention entropy are associated with reasoning breakdowns. We evaluate our approach on mathematical reasoning benchmarks (GSM8K and MATH-500) using the Qwen2.5 model family (1.5B and 3B parameters), finding statistically significant AUC improvements of up to +0.076 over output-based baselines across all tested conditions. These findings suggest that attention dispersion is a promising complement to traditional hallucination detection methods, requiring further investigation across broader model families and task domains. Comments: Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2609.18320 [cs.CL] (or arXiv:2609.18320v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2609.18320 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Shardul More [view email] [v1] Wed, 16 Sep 2026 08:40:56 UTC (269 KB) Full-text links: Access Paper: View a PDF of the paper titled Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models, by Shardul P. More and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-09 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)