Cognitive Alignment Between Humans and LLMs Across Multimodal Domains

Cognitive Alignment Between Humans and LLMs Across Multimodal Domains | 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 Cognitive Alignment Between Humans and LLMs Across Multimodal Domains Yuwei Wang, Dongqi Liang, Yi Zeng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5736241/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) show remarkable text abilities, prompting investigations into their alignment with human cognition. Using the Brain-Based Componential Semantic Representation (BBSR), a neurobiologically grounded semantic framework, we evaluate nine LLMs, including Qwen2, Llama-3, Llama-3.1, and GPT series. We examine their multimodal cognitive boundaries, representational similarity, cross-modality consistency, abstract/concrete divergences, psycholinguistic factors, and stability across repeated responses. Larger models align more closely with human cognition, particularly for concrete concepts and early-acquired words. Still, discrepancies persist, especially for abstract concepts, spatial cognition, embodied experiences (e.g., olfaction, gustation), and causal reasoning. These findings reveal limitations in LLM cognitive architectures, emphasizing models embodying human cognition. Humanities/Language and linguistics Social science/Language and linguistics Large Language Models Cognitive Alignment Cognitive Boundaries Cross-modality Consistency Concept Learning Full Text Additional Declarations There is NO Competing Interest. 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-5736241","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":407799197,"identity":"bef4ea91-44a2-4bb5-b28a-b906a5384d01","order_by":0,"name":"Yuwei Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYLCCBDDJfOAAqVrYEkjQAgE8BsSpM7iRY/jgAcNheXP+NR8P/GCwk2dgP4vfNqAWY4MEhsOGO2e83XCwhyHZsIEnL4GAltxtEgkMtxk33Di74QAPA3MCgwQBFwK1bP8B1GK/4caZBwf/MNQTpWUbMMRuJ24438NwmIfhMGEtkmfef5ZIMPifvOEGm8FhGYPjhm08Ofi18B1PS/z4oyLNdsP5w48/vqmoludnP4Nfi8IBsPOAGBgIYAYbXvVAIN8AY/EfIKR2FIyCUTAKRioAAAvWSmRwtXFYAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-2677-6563","institution":"Institute of Automation, Chinese Academy of Sciences, Beijing","correspondingAuthor":true,"prefix":"","firstName":"Yuwei","middleName":"","lastName":"Wang","suffix":""},{"id":407799198,"identity":"774c77fb-5c79-410e-94c9-3d3a66219b87","order_by":1,"name":"Dongqi Liang","email":"","orcid":"","institution":"Institute of Automation, Chinese Academy of Sciences, Beijing","correspondingAuthor":false,"prefix":"","firstName":"Dongqi","middleName":"","lastName":"Liang","suffix":""},{"id":407799199,"identity":"533d2026-8cfb-4bc0-93c7-97fe0efaaac6","order_by":2,"name":"Yi Zeng","email":"","orcid":"https://orcid.org/0000-0002-9595-9091","institution":"Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Zeng","suffix":""}],"badges":[],"createdAt":"2024-12-30 14:30:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5736241/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5736241/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80172578,"identity":"ceb9e4ab-401d-45f6-91f2-8c2634d71701","added_by":"auto","created_at":"2025-04-08 18:43:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3796269,"visible":true,"origin":"","legend":"Article File #1","description":"","filename":"CognitiveAlignmentNATHUMBEHAV2412534120250114revised.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5736241/v1_covered_c77e7db4-fd0f-4480-a313-681cf406144c.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Cognitive Alignment Between Humans and LLMs Across Multimodal Domains","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":"Large Language Models, Cognitive Alignment, Cognitive Boundaries, Cross-modality Consistency, Concept Learning","lastPublishedDoi":"10.21203/rs.3.rs-5736241/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5736241/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Large Language Models (LLMs) show remarkable text abilities, prompting investigations into their alignment with human cognition. \r\nUsing the Brain-Based Componential Semantic Representation (BBSR), a neurobiologically grounded semantic framework, we evaluate nine LLMs, including Qwen2, Llama-3, Llama-3.1, and GPT series. \r\nWe examine their multimodal cognitive boundaries, representational similarity, cross-modality consistency, abstract/concrete divergences, psycholinguistic factors, and stability across repeated responses. \r\nLarger models align more closely with human cognition, particularly for concrete concepts and early-acquired words. \r\nStill, discrepancies persist, especially for abstract concepts, spatial cognition, embodied experiences (e.g., olfaction, gustation), and causal reasoning. \r\nThese findings reveal limitations in LLM cognitive architectures, emphasizing models embodying human cognition.","manuscriptTitle":"Cognitive Alignment Between Humans and LLMs Across Multimodal Domains","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-29 04:39:38","doi":"10.21203/rs.3.rs-5736241/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":"a91b9ed4-4881-4c6e-8aa4-b39c0142b732","owner":[],"postedDate":"January 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":43479152,"name":"Humanities/Language and linguistics"},{"id":43479153,"name":"Social science/Language and linguistics"}],"tags":[],"updatedAt":"2025-04-08T18:35:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-29 04:39:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5736241","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5736241","identity":"rs-5736241","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}