Context-Aware Search: LLM-Driven Model for Searching Emerging Topics

Context-Aware Search: LLM-Driven Model for Searching Emerging Topics | 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 Context-Aware Search: LLM-Driven Model for Searching Emerging Topics Paramita Ray, Aditi Basu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6042607/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 As new topics emerge, users often struggle to find relevant and reliable information due to evolving terminology, ambiguous queries, and a lack of indexed resources. Traditional search engines may fail to capture the context and intent behind such searches, leading to suboptimal results. This study explores how Large Language Models (LLMs) can enhance query expansion and understanding of emerging topics, ensuring more effective and meaningful information retrieval. By leveraging context-aware query reformulation, semantic enrichment, and interactive refinement, LLMs can dynamically adapt search queries to improve recall, relevance, and ranking. This is particularly valuable in rapidly growing fields such as public health, finance, disaster response, and technology, where new terms and concepts emerge frequently. Our approach integrates query expansion, and neural reranking techniques to refine search intent and deliver more accurate results. The goal of this research is to develop a more adaptive, intuitive, and intelligent search framework that enhances the user experience by making web searches more precise, context-aware (Expand queries based on context rather than similarity), and informative, benefiting both general users and domain experts. Artificial Intelligence and Machine Learning Information Retrieval Query Expansion Query Refinement Large Language Model Semantic Similarity 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-6042607","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":416496025,"identity":"c16042fd-48d4-414a-9d81-1b53bf995ac1","order_by":0,"name":"Paramita Ray","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYDADNgYGxgcMDAdI0cLGwGxAmhagNWwSRGkxbz9j9uDnHrtoPvnmZ9U8NXfk+BmYHz66gUeLzJkcc8OeZ8m5bWxsZrd5jj0zlmxgMzbOwaNFgiHHTILnADNQCwNQC9vhxA0HeNik8Wrhf2Mm+edAPVAL+7dinn/EaJHIMZPmOXAYqIXHjJm3jSgtz8qNZQ4cB2rJKZac23fYWLKZkF/4k7c9fHOgOnd+8/GNH958OyzHz9788DE+LQwMHGZwJhMPiGTGqxwE2J/BmYw/CKoeBaNgFIyCkQgAgORJQMoSvuoAAAAASUVORK5CYII=","orcid":"","institution":"University of Calcutta","correspondingAuthor":true,"prefix":"","firstName":"Paramita","middleName":"","lastName":"Ray","suffix":""},{"id":416496026,"identity":"b1028c1c-0b7d-4c26-8aba-1cb76f711dd5","order_by":1,"name":"Aditi Basu","email":"","orcid":"","institution":"West Bengal State University","correspondingAuthor":false,"prefix":"","firstName":"Aditi","middleName":"","lastName":"Basu","suffix":""}],"badges":[],"createdAt":"2025-02-16 18:06:39","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-6042607/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6042607/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":76724556,"identity":"11047dae-4367-48e9-a6a9-639d23d85af5","added_by":"auto","created_at":"2025-02-20 05:09:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":270022,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6042607/v1_covered_3be2c2ea-c7ea-4fd6-b2c4-63ae19d9d8f0.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eContext-Aware Search: LLM-Driven Model for Searching Emerging Topics\u003c/p\u003e","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":"Information Retrieval, Query Expansion, Query Refinement, Large Language Model, Semantic Similarity ","lastPublishedDoi":"10.21203/rs.3.rs-6042607/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6042607/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u0026nbsp;As new topics emerge, users often struggle to find relevant and reliable information due to evolving terminology, ambiguous queries, and a lack of indexed resources. Traditional search engines may fail to capture the context and intent behind such searches, leading to suboptimal results. This study explores how Large Language Models (LLMs) can enhance query expansion and understanding of emerging topics, ensuring more effective and meaningful information retrieval. By leveraging context-aware query reformulation, semantic enrichment, and interactive refinement, LLMs can dynamically adapt search queries to improve recall, relevance, and ranking. This is particularly valuable in rapidly growing fields such as public health, finance, disaster response, and technology, where new terms and concepts emerge frequently. Our approach integrates query expansion, and neural reranking techniques to refine search intent and deliver more accurate results. The goal of this research is to develop a more adaptive, intuitive, and intelligent search framework that enhances the user experience by making web searches more precise, context-aware (Expand queries based on context rather than similarity), and informative, benefiting both general users and domain experts.\u003c/p\u003e","manuscriptTitle":"Context-Aware Search: LLM-Driven Model for Searching Emerging Topics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-20 05:08:30","doi":"10.21203/rs.3.rs-6042607/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":"76a6a530-04a0-4f67-81f8-21570355929c","owner":[],"postedDate":"February 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":44408630,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-02-20T05:08:30+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-20 05:08:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6042607","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6042607","identity":"rs-6042607","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}