The Persuasive Power of LLMs: A Systematic Literature Review and Meta-Analysis

The Persuasive Power of LLMs: A Systematic Literature Review and Meta-Analysis | 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 The Persuasive Power of LLMs: A Systematic Literature Review and Meta-Analysis Lukas Hölbling, Sebastian Maier, Stefan Feuerriegel This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7435265/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Large language models (LLMs) are increasingly used for persuasion, such as in political communication and marketing. Yet, empirical findings on the effectiveness of LLMs in persuasion compared to humans remain inconsistent. Here, we conduct a systematic literature review and meta-analysis to quantify the persuasion effect of LLMs compared to humans. We identified 8 studies with 20, 184 participants and 12 effect size estimates. We then compute the standardized effect sizes based on Hedges’ g. The results show no significant overall difference in persuasive performance between LLMs and humans (g = 0.01, p = 0.773). However, we observe substantial heterogeneity across studies (I2 = 64.78%), suggesting that persuasiveness strongly depends on contextual factors. In separate moderator analyses, no individual factor (e.g., LLM model, interaction type, or domain) reached statistical significance, which may be due to the limited number of studies. When considered jointly in a combined model, these factors explained a large proportion of the between-study variance (R2 = 83.95%), and residual heterogeneity is low (I2 = 14.30%). This suggests that differences in LLM model, interaction type, and domain interact in shaping persuasive performance, and that single-factor tests may understate their influence. Our results highlight that LLMs can match human performance in persuasion, but their success depends strongly on how they are implemented and embedded in communication contexts. Physical sciences/Mathematics and computing Biological sciences/Psychology Social science/Psychology Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 12 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 23 Sep, 2025 Reviews received at journal 18 Sep, 2025 Reviews received at journal 14 Sep, 2025 Reviewers agreed at journal 02 Sep, 2025 Reviewers agreed at journal 02 Sep, 2025 Reviewers invited by journal 02 Sep, 2025 Editor assigned by journal 02 Sep, 2025 Editor invited by journal 01 Sep, 2025 Submission checks completed at journal 31 Aug, 2025 First submitted to journal 31 Aug, 2025 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-7435265","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":510350908,"identity":"6bbe31da-4939-4b45-ab9a-1ae85be96577","order_by":0,"name":"Lukas Hölbling","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Lukas","middleName":"","lastName":"Hölbling","suffix":""},{"id":510350909,"identity":"aabcbcd5-5dd2-4e58-8eb6-1cad438a1bec","order_by":1,"name":"Sebastian Maier","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Sebastian","middleName":"","lastName":"Maier","suffix":""},{"id":510350910,"identity":"90ef2e53-25ec-45c9-bc51-404dd9a70acb","order_by":2,"name":"Stefan Feuerriegel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYBAC9gYwJQHEzI0PHoDYBwho4TkA18LYbJBAghYQYGyTIE4Le4/h48o9FnLy7o1tFYk5hxn4jjcQ0MJzxtjwzDMJIHGw7UbitsMMkmcIWGMvkWMm2XBAInHjjESIFoMbCQRskX9j/hOopX7j/IdtBWAt9x8Q0CLBY8YI1JIgL8HYxgCxBb8OoF/SikEOM9zAk9gskbgtnUfyDCGHsR/e+LHhQJ28fPvhgx8+brOW4zt+gIA1MGAAVchDpHogkG8gXu0oGAWjYBSMMAAAVLBIaoIrG7AAAAAASUVORK5CYII=","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":true,"prefix":"","firstName":"Stefan","middleName":"","lastName":"Feuerriegel","suffix":""}],"badges":[],"createdAt":"2025-08-22 14:08:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7435265/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7435265/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-30783-y","type":"published","date":"2025-12-12T15:57:20+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98243511,"identity":"f3e8079e-9430-45f6-ade8-5457d6f69cf1","added_by":"auto","created_at":"2025-12-15 16:07:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":306466,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptLLMPersuasion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7435265/v1_covered_2540ac6f-de73-4356-bfa6-a6f90d9bf435.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"The Persuasive Power of LLMs: A Systematic Literature Review and Meta-Analysis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7435265/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7435265/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Large language models (LLMs) are increasingly used for persuasion, such as in political communication and marketing. Yet, empirical findings on the effectiveness of LLMs in persuasion compared to humans remain inconsistent. Here, we conduct a systematic literature review and meta-analysis to quantify the persuasion effect of LLMs compared to humans. We identified 8 studies with 20, 184 participants and 12 effect size estimates. We then compute the standardized effect sizes based on Hedges’ g. The results show no significant overall difference in persuasive performance between LLMs and humans (g = 0.01, p = 0.773). However, we observe substantial heterogeneity across studies (I2 = 64.78%), suggesting that persuasiveness strongly depends on contextual factors. In separate moderator analyses, no individual factor (e.g., LLM model, interaction type, or domain) reached statistical significance, which may be due to the limited number of studies. When considered jointly in a combined model, these factors explained a large proportion of the between-study variance (R2 = 83.95%), and residual heterogeneity is low (I2 = 14.30%). This suggests that differences in LLM model, interaction type, and domain interact in shaping persuasive performance, and that single-factor tests may understate their influence. Our results highlight that LLMs can match human performance in persuasion, but their success depends strongly on how they are implemented and embedded in communication contexts.","manuscriptTitle":"The Persuasive Power of LLMs: A Systematic Literature Review and Meta-Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-08 01:55:36","doi":"10.21203/rs.3.rs-7435265/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-23T10:35:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-18T13:44:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-14T15:07:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"53967920953419536370668947485363381323","date":"2025-09-02T14:48:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307761863297063553575257389737196628015","date":"2025-09-02T07:52:03+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-02T07:31:16+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-02T05:59:45+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-01T16:39:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-31T18:32:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-08-31T18:31:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3baecbfb-9905-41da-911e-a022b67de42f","owner":[],"postedDate":"September 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54210181,"name":"Physical sciences/Mathematics and computing"},{"id":54210182,"name":"Biological sciences/Psychology"},{"id":54210183,"name":"Social science/Psychology"}],"tags":[],"updatedAt":"2025-12-15T16:01:00+00:00","versionOfRecord":{"articleIdentity":"rs-7435265","link":"https://doi.org/10.1038/s41598-025-30783-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-12 15:57:20","publishedOnDateReadable":"December 12th, 2025"},"versionCreatedAt":"2025-09-08 01:55:36","video":"","vorDoi":"10.1038/s41598-025-30783-y","vorDoiUrl":"https://doi.org/10.1038/s41598-025-30783-y","workflowStages":[]},"version":"v1","identity":"rs-7435265","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7435265","identity":"rs-7435265","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}