Knowledge-Aware Graph-Enhanced Transformer for Semantic Retrieval

Knowledge-Aware Graph-Enhanced Transformer for Semantic Retrieval | 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 Knowledge-Aware Graph-Enhanced Transformer for Semantic Retrieval Akshara Vinod, Linda Sara Mathew, Anand Babu N B This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9003446/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 16 You are reading this latest preprint version Abstract Neural information retrieval has transformed search systems through powerful contextual embeddings, yet struggles persist with vocabulary mismatch and lack of explicit relational knowledge. A knowledge-aware framework combines transformer-based semantic encoding with graph-structured reasoning to significantly improve document ranking accuracy. The approach automatically constructs a corpus-level knowledge graph from entity relationships, generates dense embeddings via bi-encoders with synonym expansion, and employs graph convolutional networks for multi-hop relational reasoning. Contrastive learning then aligns relevant query-document pairs while enhancing robustness. Evaluated on the MS MARCO benchmark, the method consistently outperforms lexical and dense retrieval baselines, achieving substantial gains in NDCG@10, MRR@10, and Recall@1000. These results demonstrate that integrating structured knowledge with neural representations enhances both retrieval effectiveness and interpretability, paving the way for more robust large-scale information retrieval systems. Information retrieval Knowledge graph Transformers Graph neural networks Sentence-BERT Dense retrieval Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 23 Apr, 2026 Reviews received at journal 20 Apr, 2026 Reviews received at journal 18 Apr, 2026 Reviews received at journal 16 Apr, 2026 Reviewers agreed at journal 25 Mar, 2026 Reviews received at journal 23 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers agreed at journal 21 Mar, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers invited by journal 19 Mar, 2026 Editor assigned by journal 19 Mar, 2026 Submission checks completed at journal 02 Mar, 2026 First submitted to journal 01 Mar, 2026 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-9003446","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":610758275,"identity":"6608c0b8-c4bb-4f73-8939-0fe307bd1ca9","order_by":0,"name":"Akshara Vinod","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYDAC9oYEICnBw8beABNibMClGAJ4DjwAkjYy/DwHiNUikQjSkmYjOSOBSHfpNiQnfvxRcZjH4ObrxA8/Khjk+RuY2x7g02J24FiyNM8ZoJbbuZsle84wGM44wNhugFfLwZ40ZsY2sJYN0oxtDIwbGBjbJPBqOcz/jfHnP5DDzm7+zfiPwZ6wlmMMaQy8DWk8kjN4t0kDwyqRsJYzDEC/HLPh4efJ3WbZc0wiecZhQlruPwCGWI2EPRv72c03ftTY2Pa3tz/DqwUdABUzk6J+FIyCUTAKRgFWAABCaEn2q3Qo1wAAAABJRU5ErkJggg==","orcid":"","institution":"Mar Athanasius College of Engineering","correspondingAuthor":true,"prefix":"","firstName":"Akshara","middleName":"","lastName":"Vinod","suffix":""},{"id":610758276,"identity":"9ed93579-5827-49c5-8418-0ff75f0700f9","order_by":1,"name":"Linda Sara Mathew","email":"","orcid":"","institution":"Mar Athanasius College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Linda","middleName":"Sara","lastName":"Mathew","suffix":""},{"id":610758277,"identity":"32761741-6a12-4e26-8c59-af7e7dc9e354","order_by":2,"name":"Anand Babu N B","email":"","orcid":"","institution":"National Institute of Technology Calicut","correspondingAuthor":false,"prefix":"","firstName":"Anand","middleName":"Babu N","lastName":"B","suffix":""}],"badges":[],"createdAt":"2026-03-01 19:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9003446/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9003446/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105565109,"identity":"bfda9cee-36c4-44a1-a910-2323815b4ab3","added_by":"auto","created_at":"2026-03-27 12:51:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":904648,"visible":true,"origin":"","legend":"","description":"","filename":"KAGETKnowledgeandInformationSystems3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9003446/v1_covered_d7de7102-ea45-43b5-a618-fbbff7a592e4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Knowledge-Aware Graph-Enhanced Transformer for Semantic Retrieval","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Information retrieval, Knowledge graph, Transformers, Graph neural networks, Sentence-BERT, Dense retrieval","lastPublishedDoi":"10.21203/rs.3.rs-9003446/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9003446/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Neural information retrieval has transformed search systems through powerful contextual embeddings, yet struggles persist with vocabulary mismatch and lack of explicit relational knowledge. A knowledge-aware framework combines transformer-based semantic encoding with graph-structured reasoning to significantly improve document ranking accuracy. The approach automatically constructs a corpus-level knowledge graph from entity relationships, generates dense embeddings via bi-encoders with synonym expansion, and employs graph convolutional networks for multi-hop relational reasoning. Contrastive learning then aligns relevant query-document pairs while enhancing robustness. Evaluated on the MS MARCO benchmark, the method consistently outperforms lexical and dense retrieval baselines, achieving substantial gains in NDCG@10, MRR@10, and Recall@1000. These results demonstrate that integrating structured knowledge with neural representations enhances both retrieval effectiveness and interpretability, paving the way for more robust large-scale information retrieval systems.","manuscriptTitle":"Knowledge-Aware Graph-Enhanced Transformer for Semantic Retrieval","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-24 08:51:49","doi":"10.21203/rs.3.rs-9003446/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-23T13:44:43+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-20T13:52:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-18T11:53:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-16T04:07:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34629183954551731362199769148800613563","date":"2026-03-25T11:35:23+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-23T13:54:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"181769512284026000252410166341695280268","date":"2026-03-23T08:40:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"321588043603447420711977890127844135573","date":"2026-03-23T08:10:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"18711121336569653012787643905304057221","date":"2026-03-22T01:10:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"28361319553961326406891075047656843501","date":"2026-03-21T03:23:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"77379514079114420447312181299360118891","date":"2026-03-20T07:32:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"116384443291044660865021067029955156842","date":"2026-03-20T05:26:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-19T21:03:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-19T12:15:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-02T13:20:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Knowledge and Information Systems","date":"2026-03-01T18:58:18+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f2b12f8d-9e2f-4223-9a7a-4ee1b55c973e","owner":[],"postedDate":"March 24th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-23T13:54:43+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-24 08:51:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9003446","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9003446","identity":"rs-9003446","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}