Epistemic Field Theory: Predicting Hallucination in Large Language Models via Multi-Model Consensus

Epistemic Field Theory: Predicting Hallucination in Large Language Models via Multi-Model Consensus | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Epistemic Field Theory: Predicting Hallucination in Large Language Models via Multi-Model Consensus AZRIL BIN HAMZAH, SHASHA TENG This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8785621/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Large language models exhibit hallucination—generating confident but incorrect outputs—at rates that undermine their reliability in high-stakes applications. We introduce Epistemic Field Theory (EFT), a formal framework that predicts hallucination probability from multi-model consensus. EFT defines a consensus field σ ∈ [0, 1] over query space and derives the hallucination predictor P(H) = (1 − σ) · η, where η is a model-specific noise coefficient. We establish theoretical conditions under which consensus bounds error probability and prove that independent model errors yield superlinear consensus-reliability scaling. Empirical validation across 13,728 responses from four models in three domains confirms the core prediction: consensus and hallucination correlate at r = −0.38 (p < 0.001), with hallucination rates dropping from 51.9% (σ < 0.2) to 5.9% (σ = 1.0). The framework provides a principled, model-agnostic mechanism for uncertainty-aware decision gating in automated pipelines. Artificial Intelligence and Machine Learning Hallucination detection large language models uncertainty quantification multi-model consensus epistemic uncertainty Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8785621","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":585646681,"identity":"dce72a55-2718-4389-af1c-5adc7935079a","order_by":0,"name":"AZRIL BIN HAMZAH","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAmElEQVRIiWNgGAWjYFAC5gNAQgKIGRuI1cKWwMCQQJoWHgOgFlKcxd9/5uPjwh8W0Qzsh4m0ReLA2c3GMxIkcht4Eol12MHebdI8IC0MxGqRP8zz/DdYC/9DIrUYHONhYwZrkSDWFsMzbMbSM9IkctskiLVF7vzhh58LbOpy+/nTHxCnBQSYQQQb8ephWkbBKBgFo2AU4AQAOw4oxxN1qEIAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0009-2760-6073","institution":"eptim.ai","correspondingAuthor":true,"prefix":"","firstName":"AZRIL","middleName":"BIN","lastName":"HAMZAH","suffix":""},{"id":585646682,"identity":"95d64be2-1b95-4311-a7ce-68ca4382148f","order_by":1,"name":"SHASHA TENG","email":"","orcid":"https://orcid.org/0000-0001-6188-9470","institution":"eptim.ai","correspondingAuthor":false,"prefix":"","firstName":"SHASHA","middleName":"","lastName":"TENG","suffix":""}],"badges":[],"createdAt":"2026-02-04 11:11:51","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8785621/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8785621/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101955325,"identity":"d5486a2e-1770-4777-86a0-b2347e2f52d5","added_by":"auto","created_at":"2026-02-05 11:35:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":197316,"visible":true,"origin":"","legend":"","description":"","filename":"eftjairsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8785621/v1_covered_74a6d8e6-be38-4764-b164-a22f8bb35f5d.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEpistemic Field Theory: Predicting Hallucination in Large Language Models via Multi-Model Consensus\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Hallucination detection, large language models, uncertainty quantification, multi-model consensus, epistemic uncertainty","lastPublishedDoi":"10.21203/rs.3.rs-8785621/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8785621/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLarge language models exhibit hallucination—generating confident but incorrect outputs—at rates that undermine their reliability in high-stakes applications. We introduce Epistemic Field Theory (EFT), a formal framework that predicts hallucination probability from multi-model consensus. EFT defines a consensus field σ ∈ [0, 1] over query space and derives the hallucination predictor P(H) = (1 − σ) · η, where η is a model-specific noise coefficient. We establish theoretical conditions under which consensus bounds error probability and prove that independent model errors yield superlinear consensus-reliability scaling. Empirical validation across 13,728 responses from four models in three domains confirms the core prediction: consensus and hallucination correlate at r = −0.38 (p \u0026lt; 0.001), with hallucination rates dropping from 51.9% (σ \u0026lt; 0.2) to 5.9% (σ = 1.0). The framework provides a principled, model-agnostic mechanism for uncertainty-aware decision gating in automated pipelines.\u003c/p\u003e","manuscriptTitle":"Epistemic Field Theory: Predicting Hallucination in Large Language Models via Multi-Model Consensus","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-05 11:35:09","doi":"10.21203/rs.3.rs-8785621/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b1b4fd6f-9acd-446b-9f8f-6e3b19523beb","owner":[],"postedDate":"February 5th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62306280,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-02-05T11:35:09+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-05 11:35:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8785621","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8785621","identity":"rs-8785621","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}