Automated Methodologies for Evaluating Lying, Hallucinations, and Bias in Large Language Models

Automated Methodologies for Evaluating Lying, Hallucinations, and Bias in Large Language Models | 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 Automated Methodologies for Evaluating Lying, Hallucinations, and Bias in Large Language Models George Ecurali, Zelie Thackeray This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4855434/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 As large language models become integral to various applications, ensuring the reliability and impartiality of their outputs is of paramount importance. The proposed methodologies for evaluating truthfulness, hallucinations, and bias in AI models represent a significant advancement, offering an automated and objective approach to validation without human intervention. Automated fact-checking systems, synthetic datasets, consistency analysis, and bias detection algorithms were integrated to provide a comprehensive evaluation framework. Results from these experiments indicated high accuracy in identifying truthful information, robust discernment of true versus false statements, stable performance across diverse scenarios, and effective mitigation of biases. These findings highlight the potential for enhancing AI reliability and fairness, contributing to the development of more trustworthy AI systems. Future research directions include expanding reference databases, refining synthetic datasets, and improving bias detection techniques to further enhance model evaluations. Artificial Intelligence and Machine Learning Fact-checking Hallucinations Bias detection Synthetic datasets Consistency analysis 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-4855434","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":335674062,"identity":"94bf8acb-f672-4327-8ee1-b61a30c32db7","order_by":0,"name":"George Ecurali","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAz0lEQVRIiWNgGAWjYPACCx5+BsYGkrRI8Eg2MDZC9LARqYXB4ADMGkJa5N2bn0lX1EjIGB8/3P7oRgVDHr88AQcanjlmJnnmmASP2ZnExuacMwzFkm0EbDGckcMm2cAG1HKDsbE5t40hccMxQlrmvwFq+SfBYzwDqmU/IS3yEjxsko1tEjwGEjBbCHnfgCfN2LKxT4JHAuiX2TlnJBJnHEsgYEv74Yc3G77Z2PO3H3/wOafCJrG/+QABW9DkJQi4CmRLA2E1o2AUjIJRMNIBAFLCPnqNjVvdAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0009-8149-4148","institution":"","correspondingAuthor":true,"prefix":"","firstName":"George","middleName":"","lastName":"Ecurali","suffix":""},{"id":335674063,"identity":"a66c2ab4-3887-4c3c-b25f-41cb320090e2","order_by":1,"name":"Zelie Thackeray","email":"","orcid":"https://orcid.org/0009-0007-1909-6064","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Zelie","middleName":"","lastName":"Thackeray","suffix":""}],"badges":[],"createdAt":"2024-08-04 05:21:43","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-4855434/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4855434/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61818633,"identity":"c940354a-2ea1-4b87-b284-8984968b70c0","added_by":"auto","created_at":"2024-08-06 01:04:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":266167,"visible":true,"origin":"","legend":"","description":"","filename":"george.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4855434/v1_covered_0fb04455-4107-4f4e-977c-68336a79c5a2.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAutomated Methodologies for Evaluating Lying, Hallucinations, and Bias in Large Language Models\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":false,"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":"Fact-checking, Hallucinations, Bias detection, Synthetic datasets, Consistency analysis","lastPublishedDoi":"10.21203/rs.3.rs-4855434/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4855434/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAs large language models become integral to various applications, ensuring the reliability and impartiality of their outputs is of paramount importance. The proposed methodologies for evaluating truthfulness, hallucinations, and bias in AI models represent a significant advancement, offering an automated and objective approach to validation without human intervention. Automated fact-checking systems, synthetic datasets, consistency analysis, and bias detection algorithms were integrated to provide a comprehensive evaluation framework. Results from these experiments indicated high accuracy in identifying truthful information, robust discernment of true versus false statements, stable performance across diverse scenarios, and effective mitigation of biases. These findings highlight the potential for enhancing AI reliability and fairness, contributing to the development of more trustworthy AI systems. Future research directions include expanding reference databases, refining synthetic datasets, and improving bias detection techniques to further enhance model evaluations.\u003c/p\u003e","manuscriptTitle":"Automated Methodologies for Evaluating Lying, Hallucinations, and Bias in Large Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-06 00:56:40","doi":"10.21203/rs.3.rs-4855434/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":"6eaa1ac0-ea51-4556-88f7-cdb9c6c7b0d6","owner":[],"postedDate":"August 6th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":35549666,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-08-06T00:56:40+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-06 00:56:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4855434","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4855434","identity":"rs-4855434","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}