Leveraging Large Language Models and Embedding Representations for Enhanced Word Similarity Computation

Leveraging Large Language Models and Embedding Representations for Enhanced Word Similarity Computation | 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 Leveraging Large Language Models and Embedding Representations for Enhanced Word Similarity Computation XiaoHong Peng, Hongbin Jiang, Jing Chen, MingXin Liu, Xiao Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6573106/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Current mainstream methods for computing word similarity often struggle to precisely capture the fine-grained semantics of words across different contexts. Particularly, generative semantic representations typically suffer from issues such as part-of-speech bias, semantic ambiguity, redundant exemplars, and informational redundancy, all of which compromise the accuracy of similarity measurements. To address these problems, this paper proposes WSLE, a word similarity computation framework integrating the semantic generation capabilities of large language models (LLMs) with embedding-based vector representations. First, WSLE addresses four common challenges encountered in generating semantic representations using LLMs—part-of-speech bias, redundant exemplars, semantic ambiguity, and informational redundancy. By applying constraints to lexical items, grammatical categories, semantic descriptions, and prompt length, WSLE effectively mitigates these issues, thus enabling LLMs to generate coherent, precise, and contextually rich semantic representations. Second, these generated semantic representations are transformed into high-dimensional vector embeddings via a deep semantic embedding module, facilitating quantitative assessment of semantic similarity between words. Finally, the effectiveness of WSLE is rigorously evaluated through analyses based on Pearson’s correlation coefficient (r) and Spearman’s rank correlation coefficient (ρ). Experimental results on benchmark datasets, including RG65, MC30, YP130, and MED38, demonstrate that the proposed WSLE framework significantly outperforms existing similarity computation methods, exhibiting notable advantages in accuracy and robustness for word similarity measurement tasks. Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology word similarity large language models semantic enhancement semantic embedding computational framework Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 08 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 23 Jun, 2025 Reviews received at journal 22 Jun, 2025 Reviewers agreed at journal 17 Jun, 2025 Reviews received at journal 10 Jun, 2025 Reviewers agreed at journal 14 May, 2025 Reviewers agreed at journal 14 May, 2025 Reviewers invited by journal 14 May, 2025 Editor assigned by journal 14 May, 2025 Editor invited by journal 14 May, 2025 Submission checks completed at journal 14 May, 2025 First submitted to journal 01 May, 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-6573106","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":457128149,"identity":"cf4704d0-04a5-4202-8712-8feeabbeaf07","order_by":0,"name":"XiaoHong Peng","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"XiaoHong","middleName":"","lastName":"Peng","suffix":""},{"id":457128150,"identity":"49bb027a-81e3-4abb-9961-ed96ab3b6b90","order_by":1,"name":"Hongbin Jiang","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"Hongbin","middleName":"","lastName":"Jiang","suffix":""},{"id":457128151,"identity":"a545b52b-5fef-4f69-a1e3-acf112bdfdfe","order_by":2,"name":"Jing Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYBACNobjB4z/GNjU88sfPkCcFj7GMwkFPBVpCZIz2BKI0yLHfMDgA8+ZwwkGN3gMiHQY24HEDZJth/MkZ/d8vPGGwU5Ot4GQFp6Dhw0M29KL+WXObracw5BsbHaAkBaJA2kGiW3WjDMbcrdJ8zAcSNxGUIv8A/MfB9uYGTccyHlGpBaGAwaGDWecEzfcyGEjVsuZBGOGijRjyZ5jxpZzDIjwi3wDMCoZDGzk+NmbH954U2EnR1ALCpAgNmqQtZCqYxSMglEwCkYEAADRfkYaxtGXCwAAAABJRU5ErkJggg==","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":true,"prefix":"","firstName":"Jing","middleName":"","lastName":"Chen","suffix":""},{"id":457128152,"identity":"7bbf4085-4c68-42b8-bcbc-64809fda6d0e","order_by":3,"name":"MingXin Liu","email":"","orcid":"","institution":"Guangdong Ocean University","correspondingAuthor":false,"prefix":"","firstName":"MingXin","middleName":"","lastName":"Liu","suffix":""},{"id":457128153,"identity":"5193d13e-a201-4491-b9c3-1e8579c028fc","order_by":4,"name":"Xiao Chen","email":"","orcid":"","institution":"Hebei Normal University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiao","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-05-01 16:08:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6573106/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6573106/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-31102-1","type":"published","date":"2025-12-08T15:57:56+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98243672,"identity":"56055047-76e1-41d8-bb39-cfcc4ad33bde","added_by":"auto","created_at":"2025-12-15 16:09:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":640859,"visible":true,"origin":"","legend":"","description":"","filename":"LeveragingLargeLanguageModelsandEmbeddingRepresentationsforEnhancedWordSimilarityComputation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6573106/v1_covered_57519791-f848-43df-8ace-5b5488ec8f78.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Leveraging Large Language Models and Embedding Representations for Enhanced Word Similarity Computation","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":"word similarity, large language models, semantic enhancement, semantic embedding, computational framework","lastPublishedDoi":"10.21203/rs.3.rs-6573106/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6573106/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCurrent mainstream methods for computing word similarity often struggle to precisely capture the fine-grained semantics of words across different contexts. Particularly, generative semantic representations typically suffer from issues such as part-of-speech bias, semantic ambiguity, redundant exemplars, and informational redundancy, all of which compromise the accuracy of similarity measurements. To address these problems, this paper proposes WSLE, a word similarity computation framework integrating the semantic generation capabilities of large language models (LLMs) with embedding-based vector representations. First, WSLE addresses four common challenges encountered in generating semantic representations using LLMs\u0026mdash;part-of-speech bias, redundant exemplars, semantic ambiguity, and informational redundancy. By applying constraints to lexical items, grammatical categories, semantic descriptions, and prompt length, WSLE effectively mitigates these issues, thus enabling LLMs to generate coherent, precise, and contextually rich semantic representations. Second, these generated semantic representations are transformed into high-dimensional vector embeddings via a deep semantic embedding module, facilitating quantitative assessment of semantic similarity between words. Finally, the effectiveness of WSLE is rigorously evaluated through analyses based on Pearson\u0026rsquo;s correlation coefficient (r) and Spearman\u0026rsquo;s rank correlation coefficient (ρ). Experimental results on benchmark datasets, including RG65, MC30, YP130, and MED38, demonstrate that the proposed WSLE framework significantly outperforms existing similarity computation methods, exhibiting notable advantages in accuracy and robustness for word similarity measurement tasks.\u003c/p\u003e","manuscriptTitle":"Leveraging Large Language Models and Embedding Representations for Enhanced Word Similarity Computation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-16 08:05:01","doi":"10.21203/rs.3.rs-6573106/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-23T07:12:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-22T07:58:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"100846723026859279066338070329957353251","date":"2025-06-17T11:59:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-10T08:02:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"30825447365456053188764209343105212503","date":"2025-05-14T12:10:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"273818742394046859997762897136480840216","date":"2025-05-14T12:00:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-14T11:33:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-14T11:30:05+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-14T10:59:34+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-14T06:47:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-01T15:54:51+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":"4090b110-2ab3-4d7d-8745-f11736960c9d","owner":[],"postedDate":"May 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48584825,"name":"Physical sciences/Mathematics and computing"},{"id":48584826,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":48584827,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2025-12-15T16:02:26+00:00","versionOfRecord":{"articleIdentity":"rs-6573106","link":"https://doi.org/10.1038/s41598-025-31102-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-08 15:57:56","publishedOnDateReadable":"December 8th, 2025"},"versionCreatedAt":"2025-05-16 08:05:01","video":"","vorDoi":"10.1038/s41598-025-31102-1","vorDoiUrl":"https://doi.org/10.1038/s41598-025-31102-1","workflowStages":[]},"version":"v1","identity":"rs-6573106","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6573106","identity":"rs-6573106","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}