Narratives of Divide: The Polarizing Power of Large Language Models in a Turbulent World

Narratives of Divide: The Polarizing Power of Large Language Models in a Turbulent World | 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 Narratives of Divide: The Polarizing Power of Large Language Models in a Turbulent World Khalid Saqr This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5950965/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 (LLMs) are reshaping information consumption and influencing public discourse, raising concerns about their potential to empower narrative control and amplify polarisation. This study examines the embedded worldviews of four LLMs across key themes using Wittgenstein’s theory of language games to interpret meaning and narrative structures. A two-tiered methodology—Surface (-S) and Deep (-D) analyses—is applied using Natural Language Processing (NLP) to investigate four different LLMs. The -S analysis, evaluating general differences in thematic focus, semantic similarity, and sentiment pattern, found no significant variability across the four LLMs. However, the -D analysis, employing zero-shot classification across geopolitical, ideological, and philosophical dimensions, revealed alarming differences. Liberalism (H = 12.51, p = 0.006) , conservatism (H = 8.76, p = 0.033) , and utilitarianism (H = 8.56, p = 0.036) emerged as key points of divergence between LLMs. For example, the narratives constructed by one LLM exhibited strong pro-globalization and liberal leanings, while another generated pro-sovereignty narratives, introducing meaning through national security and state autonomy frames. Differences in philosophical perspectives further highlighted contrasting preferences for utilitarian versus deontological reasoning across justice and security themes. These findings demonstrate that LLMs, when deployed at a sufficient scale and connectivity, could be employed as stealth weapons in narrative warfare. Artificial Intelligence and Machine Learning Behavioral Economics Sociology Other Political Science International Relations Media Studies Philosophy Language games computational philosophy large language models geopolitical polarisation narrative warfare 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-5950965","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":410896050,"identity":"4866c4ed-8165-40ae-ae56-eb5a2323374b","order_by":0,"name":"Khalid Saqr","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYBACCQkGxgMJbDYGYA5UkJmQFgagljRStTCwHSZBi+Ts5gcHHpSdNzZn7zG8zbuDQZ6fgcfYAJ8WaZljBgcSzt02s+w5Y2zNe4bBcGYDj3ECPi1yEgkGBxLbbtsY3MjdJs3bxgDk8hgfwK8l/QNQyzkStEhL5IBsOWCGogWvwyRn5BQA/ZJsbHDm/GfLuW0ShjOb2Yrxel/iRvrGhz/K7Aw3HG9LvPG2zUaen715swQ+LSiAiQcUNfhjBQ0w/iBF9SgYBaNgFIwYAAB2JEgNa9tLlgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-3058-2705","institution":"KNOWDYN","correspondingAuthor":true,"prefix":"","firstName":"Khalid","middleName":"","lastName":"Saqr","suffix":""}],"badges":[],"createdAt":"2025-02-03 12:22:51","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-5950965/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5950965/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":75691102,"identity":"e5af86db-711f-4e8a-aeb4-53c32e7c97d6","added_by":"auto","created_at":"2025-02-07 07:16:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1167238,"visible":true,"origin":"","legend":"","description":"","filename":"NarrativesOfDivide.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5950965/v1_covered_c78a1785-ff95-4192-8b2f-a1d3f266a85c.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eNarratives of Divide: The Polarizing Power of Large Language Models in a Turbulent World\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"KNOWDYN","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":"Language games, computational philosophy, large language models, geopolitical polarisation, narrative warfare","lastPublishedDoi":"10.21203/rs.3.rs-5950965/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5950965/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLarge language models (LLMs) are reshaping information consumption and influencing public discourse, raising concerns about their potential to empower narrative control and amplify polarisation. This study examines the embedded worldviews of four LLMs across key themes using Wittgenstein\u0026rsquo;s theory of language games to interpret meaning and narrative structures. A two-tiered methodology\u0026mdash;Surface (-S) and Deep (-D) analyses\u0026mdash;is applied using Natural Language Processing (NLP) to investigate four different LLMs. The -S analysis, evaluating general differences in thematic focus, semantic similarity, and sentiment pattern, found no significant variability across the four LLMs. However, the -D analysis, employing zero-shot classification across geopolitical, ideological, and philosophical dimensions, revealed alarming differences. Liberalism \u003cb\u003e(H\u0026thinsp;=\u0026thinsp;12.51, p\u0026thinsp;=\u0026thinsp;0.006)\u003c/b\u003e, conservatism \u003cb\u003e(H\u0026thinsp;=\u0026thinsp;8.76, p\u0026thinsp;=\u0026thinsp;0.033)\u003c/b\u003e, and utilitarianism \u003cb\u003e(H\u0026thinsp;=\u0026thinsp;8.56, p\u0026thinsp;=\u0026thinsp;0.036)\u003c/b\u003e emerged as key points of divergence between LLMs. For example, the narratives constructed by one LLM exhibited strong pro-globalization and liberal leanings, while another generated pro-sovereignty narratives, introducing meaning through national security and state autonomy frames. Differences in philosophical perspectives further highlighted contrasting preferences for utilitarian versus deontological reasoning across justice and security themes. These findings demonstrate that LLMs, when deployed at a sufficient scale and connectivity, could be employed as stealth weapons in narrative warfare.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e","manuscriptTitle":"Narratives of Divide: The Polarizing Power of Large Language Models in a Turbulent World","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-07 07:08:07","doi":"10.21203/rs.3.rs-5950965/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":"f11181d1-2820-4ff0-8fd6-8c3c4ef05285","owner":[],"postedDate":"February 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":43766733,"name":"Artificial Intelligence and Machine Learning"},{"id":43766734,"name":"Behavioral Economics"},{"id":43766735,"name":"Sociology"},{"id":43766736,"name":"Other Political Science"},{"id":43766737,"name":"International Relations"},{"id":43766738,"name":"Media Studies"},{"id":43766739,"name":"Philosophy"}],"tags":[],"updatedAt":"2025-02-07T07:08:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-07 07:08:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5950965","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5950965","identity":"rs-5950965","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}