Exploring Universal Human Values with Large Language Models: The AWARE-Value Model

Exploring Universal Human Values with Large Language Models: The AWARE-Value Model | 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 Exploring Universal Human Values with Large Language Models: The AWARE-Value Model Xin Zhang, Yuanyi Ren, Zheng Guo, Lai Wei, Tianrui Huo, Haoran Ye, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8188052/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Human values play a vital role in everyday functioning, yet their underlying structure remains incompletely understood—for instance, how many core values truly exist, and how these values are organized. Traditional value theories often employ a top-down approach, relying on expert-defined constructs, whereas bottom-up methods (e.g., the psycholexical approach) are data-driven but suffer from limited scale and manual effort. In this study, we leverage advances in large language models (LLMs) to construct a comprehensive value structure. Combining top-down and bottom-up perspectives, we first automatically extracted 4,648 values from vast, diverse, and longitudinal internet corpora, which were refined into 521 key value descriptors using an efficient embedding-based semantic filtering process. Next, to uncover the structure of the value space, we applied LLMs to analyze 392,843 textual passages from 10,995 individuals, quantifying individual tendencies across these value descriptors. Our analysis successfully uncovers the latent organization of human values into a five-factor structure, which we term AWARE: Authenticity, Well-Being, Actualization, Relatedness, and Epistemic Need. This value structures showed high consistency when compared to a parallel human-validated system (N=2,300). Psychometric analysis further confirmed the robustness and reliability of the proposed value structure. We then rigorously validated this structure through data-driven validation across three cross-cultural survey datasets (N = 164,809), which established its robust predictive power. Collectively, these results provide compelling evidence for the reliability, generalizability, and practical relevance of the proposed AWARE structure of the value space. Social science/Psychology/Human behaviour Social science/Science, technology and society human values psycholexical approach psychometrics LLM Full Text Additional Declarations There is NO Competing Interest. We confirmed that the study involving human subjects has received participant's formal consent. Cite Share Download PDF Status: Under Review 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-8188052","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":581255344,"identity":"08bd270c-e187-4996-8be5-cc359cea0c2b","order_by":0,"name":"Xin Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYDACCQglx8ADothI0GJMupbEBqK1yM9ufvbwC8Ph9O08ZwwYPpQdZuCf3YBfC+OcY+bGMgxpuTt7ewwYZ5w7zCBx5wB+LcwSCWbSEgw2uRvO8xgw87YdZjCQSMCvhU0i/RtQi0S6AUjLX2K08EjkmEl+YLBJMDjbY8DMSIwWCYmcMmkGgzTDnT3HCg72nEvnkbhBQIv8jPRtkj8qDsub8yRvfPCjzFqOfwYBLSDAzGPAwABEDAdALiWsHggYfzBAtIyCUTAKRsEowAoAmdU6MSycxHoAAAAASUVORK5CYII=","orcid":"","institution":"Peking University","correspondingAuthor":true,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zhang","suffix":""},{"id":581255345,"identity":"cb88ab2d-c973-4746-9d1d-edcd9e1bca34","order_by":1,"name":"Yuanyi Ren","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yuanyi","middleName":"","lastName":"Ren","suffix":""},{"id":581255346,"identity":"b06819e2-3e92-45b8-a654-3a307ef2c4e8","order_by":2,"name":"Zheng Guo","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Zheng","middleName":"","lastName":"Guo","suffix":""},{"id":581255347,"identity":"1de3d50d-b6a7-4eb8-80e1-a8a25f6b44b5","order_by":3,"name":"Lai Wei","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Lai","middleName":"","lastName":"Wei","suffix":""},{"id":581255348,"identity":"46234eab-ca53-435f-b4f5-d046a423195a","order_by":4,"name":"Tianrui Huo","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Tianrui","middleName":"","lastName":"Huo","suffix":""},{"id":581255349,"identity":"352a69b2-e3e6-41bf-9850-f049b8c2632b","order_by":5,"name":"Haoran Ye","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Haoran","middleName":"","lastName":"Ye","suffix":""},{"id":581255350,"identity":"199cf691-9219-43a4-accb-0330abef4a95","order_by":6,"name":"Yuhang Xie","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Yuhang","middleName":"","lastName":"Xie","suffix":""},{"id":581255351,"identity":"f17ed73e-1c11-4607-ae2b-2f3ec262dffb","order_by":7,"name":"Guojie Song","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Guojie","middleName":"","lastName":"Song","suffix":""}],"badges":[],"createdAt":"2025-11-24 00:35:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8188052/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8188052/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101880592,"identity":"a0a9b8b1-5c54-4312-addd-573a925ed9a0","added_by":"auto","created_at":"2026-02-04 15:04:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1487450,"visible":true,"origin":"","legend":"Article File","description":"","filename":"humanvaluesystemanonymous.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8188052/v1_covered_d8e65af4-8ca9-4443-a93d-338baa65db0a.pdf"}],"financialInterests":"\u003cp\u003eThere is \u003cstrong\u003eNO\u003c/strong\u003e Competing Interest.\u003c/p\u003e\n\u003cp\u003eWe confirmed that the study involving human subjects has received participant's formal consent.\u003c/p\u003e","formattedTitle":"Exploring Universal Human Values with Large Language Models: The AWARE-Value Model","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"human values, psycholexical approach, psychometrics, LLM","lastPublishedDoi":"10.21203/rs.3.rs-8188052/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8188052/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Human values play a vital role in everyday functioning, yet their underlying structure remains incompletely understood—for instance, how many core values truly exist, and how these values are organized. Traditional value theories often employ a top-down approach, relying on expert-defined constructs, whereas bottom-up methods (e.g., the psycholexical approach) are data-driven but suffer\r\nfrom limited scale and manual effort. In this study, we leverage advances in large language models (LLMs) to construct a comprehensive value structure. Combining top-down and bottom-up perspectives, we first automatically extracted 4,648 values from vast, diverse, and longitudinal internet corpora, which were refined into 521 key value descriptors using an efficient embedding-based semantic filtering process. Next, to uncover the structure of the value space, we applied LLMs to analyze 392,843 textual passages from 10,995 individuals, quantifying individual tendencies across these value descriptors. Our analysis successfully uncovers the latent organization of human values into a five-factor structure, which we term AWARE: Authenticity, Well-Being, Actualization, Relatedness,\r\nand Epistemic Need. This value structures showed high consistency when compared to a parallel human-validated system (N=2,300). Psychometric analysis further confirmed the robustness and reliability of the proposed value structure. We then rigorously validated this structure through data-driven validation across three cross-cultural survey datasets (N = 164,809), which established its robust predictive power. Collectively, these results provide compelling evidence for the reliability, generalizability, and practical relevance of the proposed AWARE structure of the value space.","manuscriptTitle":"Exploring Universal Human Values with Large Language Models: The AWARE-Value Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-30 17:46:22","doi":"10.21203/rs.3.rs-8188052/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-human-behaviour","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"nathumbehav","sideBox":"Learn more about [Nature Human Behaviour](http://www.nature.com/nathumbehav/)","snPcode":"","submissionUrl":"","title":"Nature Human Behaviour","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"acf710e6-0555-468a-849e-2e85891f96f0","owner":[],"postedDate":"January 30th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":61837590,"name":"Social science/Psychology/Human behaviour"},{"id":61837591,"name":"Social science/Science, technology and society"}],"tags":[],"updatedAt":"2026-03-25T14:41:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-30 17:46:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8188052","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8188052","identity":"rs-8188052","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}