Deepening Citation Understanding in Scientific Literature via LLM-Powered Context Extraction

Deepening Citation Understanding in Scientific Literature via LLM-Powered Context Extraction | 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 Deepening Citation Understanding in Scientific Literature via LLM-Powered Context Extraction Thu Huong Nguyen, Cedric Pruski, Marcos Da Silveira This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8640955/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 Scientific progress relies on the complex, interconnected web of scholarly publications housed within digital libraries. While citations are the core mechanism for linking this knowledge, the simple reference alone fails to capture the intricate context in which the cited work is discussed. This lack of context poses a significant challenge for digital library algorithms seeking to understand scholarly influence. To address this, Citation Context Extraction (CCE) is a foundational task for transforming raw citations into meaningful, semantically rich links that can power advanced bibliometric analysis. This paper presents a novel, two-fold methodology for enhancing the CCE process. We first introduce an improved CCE method that leverages a richer set of textual features to more accurately identify citation context sentences, advancing beyond existing state-of-the-art techniques. Second, we propose an original approach that utilizes Large Language Models (LLMs) and advanced prompt engineering to perform a deeper, more nuanced and explainable semantic interpretation of the extracted contexts. We validate our methods on two distinct scientific corpora: ACL-ARC, a specialized dataset from computational linguistics and SDP-ACT, a more generic dataset spanning multiple disciplines. The results of our comparative analysis against state-of-the-art models demonstrate a significant improvement in CCE quality. Our contributions provide a crucial step toward building more intelligent and interpretable knowledge discovery systems, unlocking the full potential of digital libraries as platforms for understanding and mapping the intellectual lineage of scientific discourse. Citation Context Citation Classification Large Language Model Scientific Literature Analysis Full Text Additional Declarations No competing interests reported. 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-8640955","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":581005095,"identity":"a8cbf710-b915-43ce-b946-97f849ec0c74","order_by":0,"name":"Thu Huong Nguyen","email":"","orcid":"","institution":"Luxembourg Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Thu","middleName":"Huong","lastName":"Nguyen","suffix":""},{"id":581005096,"identity":"02a2863d-a8e9-457d-829c-d48715e95f08","order_by":1,"name":"Cedric Pruski","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie3QPQqDMBTA8RcEuwRcX0HwCgGHdij0KslSF3Fx6eAQEPQKDtIeouCsCE4eoKPF1aFjx4YWoZOhW6H5Ty+QH/kAMJl+Mwb8PVjAj1uqBlJ/QXqkYAPoCcyEZAha4uRpdR8SiDZFMLLbCV3vLKGlCwT7Li54B7F7DX0uKqSsg2XCMPRBSBAFhlb9IraOeNNMgrEWJVIv055CZ8LVxaT6Md3FsD/EwDuMkU4+U4N6i5BNuUCcvL2QR7KLcBWMazXsvbRthmmBzIfxjwWReqDi2h0mk8n0vz0BMcZFGCwLvfIAAAAASUVORK5CYII=","orcid":"","institution":"Luxembourg Institute of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Cedric","middleName":"","lastName":"Pruski","suffix":""},{"id":581005098,"identity":"620a8b4a-3c7a-40b3-bf1b-90a24a0d4b60","order_by":2,"name":"Marcos Da Silveira","email":"","orcid":"","institution":"Luxembourg Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Marcos","middleName":"Da","lastName":"Silveira","suffix":""}],"badges":[],"createdAt":"2026-01-19 15:37:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8640955/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8640955/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101398448,"identity":"8835d091-3e5a-40d6-a7a0-88361a429651","added_by":"auto","created_at":"2026-01-29 09:41:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":369274,"visible":true,"origin":"","legend":"","description":"","filename":"Archive.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8640955/v1_covered_f379716a-db3c-407c-8355-54e2c2c06f45.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deepening Citation Understanding in Scientific Literature via LLM-Powered Context Extraction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Citation Context, Citation Classification, Large Language Model, Scientific Literature Analysis","lastPublishedDoi":"10.21203/rs.3.rs-8640955/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8640955/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Scientific progress relies on the complex, interconnected web of scholarly publications housed within digital libraries. While citations are the core mechanism for linking this knowledge, the simple reference alone fails to capture the intricate context in which the cited work is discussed. This lack of context poses a significant challenge for digital library algorithms seeking to understand scholarly influence. To address this, Citation Context Extraction (CCE) is a foundational task for transforming raw citations into meaningful, semantically rich links that can power advanced bibliometric analysis. This paper presents a novel, two-fold methodology for enhancing the CCE process. We first introduce an improved CCE method that leverages a richer set of textual features to more accurately identify citation context sentences, advancing beyond existing state-of-the-art techniques. Second, we propose an original approach that utilizes Large Language Models (LLMs) and advanced prompt engineering to perform a deeper, more nuanced and explainable semantic interpretation of the extracted contexts. We validate our methods on two distinct scientific corpora: ACL-ARC, a specialized dataset from computational linguistics and SDP-ACT, a more generic dataset spanning multiple disciplines. The results of our comparative analysis against state-of-the-art models demonstrate a significant improvement in CCE quality. Our contributions provide a crucial step toward building more intelligent and interpretable knowledge discovery systems, unlocking the full potential of digital libraries as platforms for understanding and mapping the intellectual lineage of scientific discourse.","manuscriptTitle":"Deepening Citation Understanding in Scientific Literature via LLM-Powered Context Extraction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-28 22:57:42","doi":"10.21203/rs.3.rs-8640955/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":"927259af-9239-4675-a7d6-40721697e942","owner":[],"postedDate":"January 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-18T07:23:58+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-28 22:57:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8640955","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8640955","identity":"rs-8640955","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}