Dialogues on Democracy: Belief-Tailored AI Conversations Reduce Inaccurate Election Denial Beliefs

Dialogues on Democracy: Belief-Tailored AI Conversations Reduce Inaccurate Election Denial Beliefs | 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 Article Dialogues on Democracy: Belief-Tailored AI Conversations Reduce Inaccurate Election Denial Beliefs Shaye-Ann Hopkins, Thomas Costello, Gordon Pennycook, David Rand This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8663921/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 Elections, while central to democratic functioning, have become increasingly threatened by beliefs about election fraud. Artificial intelligence (AI) provides a novel opportunity to address such false beliefs through dynamic conversation and debunking. Through two experiments (N = 1,802 Republicans from Lucid who endorsed election fraud claims), we examined the use of AI to fact-check 2020 election conspiracies prior to the 2024 US Presidential election. We tested the effects of two treatments (an information-tailored and values-tailored AI dialogue) in which AI fact-checked their claims and tailored arguments to the specific election conspiracy that the participant themselves articulated. Both treatment conditions, when compared to a control dialogue and a simple statement that the conspiracy was incorrect, reduced confidence in their election conspiracy claims. There was no significant difference between information-tailored and values-tailored feedback. Promisingly, participants with the strongest baseline denialism experienced the largest decreases in denialism beliefs. These studies highlight the potential of AI-driven interventions to address election misinformation. Scientific community and society/Social sciences/Decision making Scientific community and society/Social sciences/Psychology/Human behaviour AI LLM elections conspiracies belief updating election fraud Full Text Additional Declarations There is NO Competing Interest. Supplementary Files AIElectionsPaperSupplement.pdf Supplementary Information 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-8663921","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":580732659,"identity":"7c7298b0-e39f-44ba-a525-d9dde6a6b82d","order_by":0,"name":"Shaye-Ann Hopkins","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYJCCAx//2TA28ICYbMTpYDw4gy2NNC3Mh3nYDpOgRX7a6YTDPDznZTecOXyA4UPZYcJaDG7nbjg4R+K28YazbQmMM84Ro0U6d8OBNwa3Ezec5zFg5m0jQov8bKAWnoRzQC38H5j/EqOFAeQwngMHEjec7WFgZiRGC9gvMxuSjWeeOWZwsOdcOlEO2/zhY4OdbN+Z5IcPfpRZE+EwZHCARPWjYBSMglEwCnABANwPRohZPtXSAAAAAElFTkSuQmCC","orcid":"","institution":"Vienna University of Economics and Business","correspondingAuthor":true,"prefix":"","firstName":"Shaye-Ann","middleName":"","lastName":"Hopkins","suffix":""},{"id":580732660,"identity":"f14f4784-42ee-43ac-9ced-3366805eca1d","order_by":1,"name":"Thomas Costello","email":"","orcid":"","institution":"Carnegie Mellon University","correspondingAuthor":false,"prefix":"","firstName":"Thomas","middleName":"","lastName":"Costello","suffix":""},{"id":580732661,"identity":"89e60c9f-f871-45d3-b7ee-5f845dbeb199","order_by":2,"name":"Gordon Pennycook","email":"","orcid":"https://orcid.org/0000-0003-1344-6143","institution":"Cornell University","correspondingAuthor":false,"prefix":"","firstName":"Gordon","middleName":"","lastName":"Pennycook","suffix":""},{"id":580732662,"identity":"f127e155-59a4-4193-91e1-60200941c8ed","order_by":3,"name":"David Rand","email":"","orcid":"https://orcid.org/0000-0001-8975-2783","institution":"Massachusetts Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Rand","suffix":""}],"badges":[],"createdAt":"2026-01-22 00:05:25","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-8663921/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8663921/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101297805,"identity":"e487d21a-25da-4c11-aa1a-95a775273874","added_by":"auto","created_at":"2026-01-28 09:28:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":708690,"visible":true,"origin":"","legend":"Article File","description":"","filename":"AIElectionsPaperNatureComms.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8663921/v1_covered_e27a55ae-eb7f-4ca2-8157-a1932183c8e8.pdf"},{"id":101277753,"identity":"9edbcb0d-019a-45f8-a398-19fc2555d42c","added_by":"auto","created_at":"2026-01-28 04:06:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":3042159,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"AIElectionsPaperSupplement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8663921/v1/ddb93b4b6ef4d79cd59b741f.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Dialogues on Democracy: Belief-Tailored AI Conversations Reduce Inaccurate Election Denial Beliefs","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":"AI, LLM, elections, conspiracies, belief updating, election fraud","lastPublishedDoi":"10.21203/rs.3.rs-8663921/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8663921/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Elections, while central to democratic functioning, have become increasingly threatened by beliefs about election fraud. Artificial intelligence (AI) provides a novel opportunity to address such false beliefs through dynamic conversation and debunking. Through two experiments (N = 1,802 Republicans from Lucid who endorsed election fraud claims), we examined the use of AI to fact-check 2020 election conspiracies prior to the 2024 US Presidential election. We tested the effects of two treatments (an information-tailored and values-tailored AI dialogue) in which AI fact-checked their claims and tailored arguments to the specific election conspiracy that the participant themselves articulated. Both treatment conditions, when compared to a control dialogue and a simple statement that the conspiracy was incorrect, reduced confidence in their election conspiracy claims. There was no significant difference between information-tailored and values-tailored feedback. Promisingly, participants with the strongest baseline denialism experienced the largest decreases in denialism beliefs. These studies highlight the potential of AI-driven interventions to address election misinformation.","manuscriptTitle":"Dialogues on Democracy: Belief-Tailored AI Conversations Reduce Inaccurate Election Denial Beliefs","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-28 04:06:30","doi":"10.21203/rs.3.rs-8663921/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":"7969a250-fcc6-4434-998e-a6e8a6aedb4e","owner":[],"postedDate":"January 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":61779300,"name":"Scientific community and society/Social sciences/Decision making"},{"id":61779301,"name":"Scientific community and society/Social sciences/Psychology/Human behaviour"}],"tags":[],"updatedAt":"2026-01-28T04:06:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-28 04:06:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8663921","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8663921","identity":"rs-8663921","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}