Leveraging Large Language Models for Document Classification in the Banking Sector | 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 Leveraging Large Language Models for Document Classification in the Banking Sector Rómulo Nogueira, Hugo Mentzingen, Nuno Garcia This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7511605/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 06 Apr, 2026 Read the published version in International Journal of Data Science and Analytics → Version 1 posted 11 You are reading this latest preprint version Abstract Document classification serves as foundational step in critical tasks such as information extraction, analysis and decision-making. However, existing approaches often struggle with the variability, volume, and complexity of real-world documents. These methods are further limited by a lack of configurability and explainability, requiring specialized technical expertise to accommodate diverse user needs and often producing results that are difficult to interpret. To address the complexities of modern document processing, this paper introduces a novel zero-shot document classification framework that leverages Large Language Models (LLMs), designed for accessibility and configurability by both technical and non-technical users. Unlike traditional methods, which require extensive labeled data, the zero-shot configuration enables our framework to perform the classification task without any prior exposure to labeled examples of the target categories, relying instead on semantic understanding derived from user-provided label descriptions and document content. Developed and validated using a real-world banking dataset, our framework leverages different strategies for providing context to LLMs during classification. Experimental results demonstrate substantial improvements in both accuracy and efficiency, outperforming current zero-shot methods while also reducing operating costs. Document Classification Large Language Models Banking Sector Retrieval-Augmented Generation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 06 Apr, 2026 Read the published version in International Journal of Data Science and Analytics → Version 1 posted Editorial decision: Revision requested 15 Nov, 2025 Reviews received at journal 10 Nov, 2025 Reviews received at journal 24 Oct, 2025 Reviews received at journal 22 Oct, 2025 Reviewers agreed at journal 17 Oct, 2025 Reviewers agreed at journal 15 Oct, 2025 Reviewers agreed at journal 14 Oct, 2025 Reviewers invited by journal 14 Oct, 2025 Editor assigned by journal 25 Sep, 2025 Submission checks completed at journal 02 Sep, 2025 First submitted to journal 01 Sep, 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-7511605","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":534464082,"identity":"6cee3b83-c4ae-42df-9d77-b79f24713b73","order_by":0,"name":"Rómulo Nogueira","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIie3RMQuCQBTA8RcHujxwPdHoK1wIiSD5VQTBKcGWaA9sqd3vETQbB03S3CpBU0MOgUNQXo2SNgbdf7obfrw7HoBM9sMhAMkoxOLwPVF8CgwQFXH3v1NMEOgk9nK9K26Ja9rLvDxemWt6g0VGptVnYuaHwOonIZp5tHFSFtYPU3yStkyhdDIy9IQjhWhrIOM1QUawmzyQapezcX8R7dpJ9DLJsD4oBrynQDvB3LLgENTkbDkr8Zd9yHgathB1NSyq2dijWlAcq7nrqQtenGL3MxGRxsZ5OwDoNZZAuohMJpP9VU/APUFcm/xHpAAAAABJRU5ErkJggg==","orcid":"","institution":"Deloitte Technology","correspondingAuthor":true,"prefix":"","firstName":"Rómulo","middleName":"","lastName":"Nogueira","suffix":""},{"id":534464083,"identity":"8db237ac-01b9-43b5-8b72-a175e1ba328b","order_by":1,"name":"Hugo Mentzingen","email":"","orcid":"","institution":"Deloitte Technology","correspondingAuthor":false,"prefix":"","firstName":"Hugo","middleName":"","lastName":"Mentzingen","suffix":""},{"id":534464084,"identity":"0d235503-3ae7-403a-af99-ac79eb733192","order_by":2,"name":"Nuno Garcia","email":"","orcid":"","institution":"University of Lisbon","correspondingAuthor":false,"prefix":"","firstName":"Nuno","middleName":"","lastName":"Garcia","suffix":""}],"badges":[],"createdAt":"2025-09-01 21:38:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7511605/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7511605/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s41060-026-01077-x","type":"published","date":"2026-04-06T15:58:37+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94457496,"identity":"c7f5a71b-d6b4-440b-b804-d72db665950d","added_by":"auto","created_at":"2025-10-27 14:45:59","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5067,"visible":true,"origin":"","legend":"","description":"","filename":"7931305ae6f44c31896c09ac83383b03.json","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/133c545cea5bd17079b629cf.json"},{"id":94457498,"identity":"eff6294b-e3ff-4f6f-a091-3205815e95c9","added_by":"auto","created_at":"2025-10-27 14:45:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52303,"visible":true,"origin":"","legend":"","description":"","filename":"CoverLetter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/22aace2eb90b88845aa6cb9b.pdf"},{"id":94457041,"identity":"cbfbff72-0fc5-480d-85b8-1a5b6f0c7660","added_by":"auto","created_at":"2025-10-27 14:45:25","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99978,"visible":true,"origin":"","legend":"","description":"","filename":"DiagramaAbstract.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/9f032e63dbfc8be540fc6861.png"},{"id":94457392,"identity":"6b371b33-2850-44f7-9274-f32c28709688","added_by":"auto","created_at":"2025-10-27 14:45:50","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":586398,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerJournal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/83ab52020beb32cbf5e98a08.pdf"},{"id":94457315,"identity":"ff308839-48d9-49e0-a125-06a0cba2018a","added_by":"auto","created_at":"2025-10-27 14:45:41","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33693,"visible":true,"origin":"","legend":"","description":"","filename":"crpcpu.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/3070621b67210218f911f173.png"},{"id":94457652,"identity":"808d6190-76b4-4263-bcf2-2c1494e35eed","added_by":"auto","created_at":"2025-10-27 14:46:07","extension":"eps","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/0b9588e1df572b84b427211b.eps"},{"id":94456994,"identity":"5f7bee9c-2179-4ba2-8726-b15854250a33","added_by":"auto","created_at":"2025-10-27 14:45:20","extension":"eps","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/2393cae5beba9b3586b07a65.eps"},{"id":94457440,"identity":"c69beafb-79f4-46f9-bd63-45d71204a965","added_by":"auto","created_at":"2025-10-27 14:45:56","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":63520,"visible":true,"origin":"","legend":"","description":"","filename":"frameworkllmcall.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/2fe8cc933c1ef17e77146457.png"},{"id":94456672,"identity":"935365f0-81ae-4a3c-a60d-109d5c7ff7b8","added_by":"auto","created_at":"2025-10-27 14:44:54","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87527,"visible":true,"origin":"","legend":"","description":"","filename":"inputprompt.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/ced104985d1e445db2747779.png"},{"id":94457042,"identity":"45988bad-2143-4efe-a0ec-c636ed206dcd","added_by":"auto","created_at":"2025-10-27 14:45:25","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23886,"visible":true,"origin":"","legend":"","description":"","filename":"oth.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/72598295e6e1ee83b560af3e.png"},{"id":94457366,"identity":"4aa5ef5b-d744-477a-9e0b-1bc9fac2e240","added_by":"auto","created_at":"2025-10-27 14:45:48","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17921,"visible":true,"origin":"","legend":"","description":"","filename":"outputprompt.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/e40d174407ac40b84a2a2bdd.png"},{"id":94457605,"identity":"bea2c985-65ea-47c6-909e-21e50b25763d","added_by":"auto","created_at":"2025-10-27 14:46:04","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124599,"visible":true,"origin":"","legend":"","description":"","filename":"rag.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/2331dbe95d0a6270fa85d888.png"},{"id":94456673,"identity":"c7eeae16-a76f-4cab-84d4-e30b30e183b8","added_by":"auto","created_at":"2025-10-27 14:44:54","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/6c3c2899bcb9a7beb26e6dc5.bst"},{"id":94457284,"identity":"cc32e096-4691-441d-9fbe-a263236eed8a","added_by":"auto","created_at":"2025-10-27 14:45:38","extension":"bst","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/3e188c389b30489161a38959.bst"},{"id":94457575,"identity":"737ebba0-4cfc-4595-9bf4-de754ed9a462","added_by":"auto","created_at":"2025-10-27 14:46:01","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/4c3a0bd4f01bb4c8e5f55c2d.bst"},{"id":94456848,"identity":"e7dedf82-2aaa-43fc-afe8-c72d14694c8f","added_by":"auto","created_at":"2025-10-27 14:45:12","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/b5b10392f1fbaec20f7aa707.bst"},{"id":94457048,"identity":"6fd01ea8-7823-4eef-a0a8-ac9b915fbc42","added_by":"auto","created_at":"2025-10-27 14:45:26","extension":"cls","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/071a2aab7ca1823e5d017534.cls"},{"id":94457044,"identity":"7e9a6939-ed45-4561-b3bd-e39e90163acb","added_by":"auto","created_at":"2025-10-27 14:45:26","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/13238951f6242270931822a3.bst"},{"id":94457417,"identity":"4fea9ce5-2eea-4c4f-b79e-80a0fe100134","added_by":"auto","created_at":"2025-10-27 14:45:53","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64180,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/deea0a96bcb993545c5895b3.bst"},{"id":94457039,"identity":"d3dc1653-1dda-4620-8786-1ac87142ba28","added_by":"auto","created_at":"2025-10-27 14:45:24","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/b628e044fedcf42cf1f37bab.bst"},{"id":94457655,"identity":"013a8cd1-238b-4b70-88b1-f4d550653a25","added_by":"auto","created_at":"2025-10-27 14:46:08","extension":"bst","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/d4255964bc236a22572671ef.bst"},{"id":94456997,"identity":"41e54b9d-ff84-41e0-b87c-ff86bcb61819","added_by":"auto","created_at":"2025-10-27 14:45:20","extension":"bst","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/789e8451c50db524610e5ae9.bst"},{"id":94457580,"identity":"04b80ed5-ddb9-474e-8fb2-6e3ebf768eaf","added_by":"auto","created_at":"2025-10-27 14:46:02","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43795,"visible":true,"origin":"","legend":"","description":"","filename":"tokenizersretrieval.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/e193cba91d8f1b694d68c1d3.png"},{"id":94457412,"identity":"bb1f95dc-51f8-46f6-810c-d5995e256107","added_by":"auto","created_at":"2025-10-27 14:45:52","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49904,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineDiagramaAbstract.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/24e04d97f441ab8fac46f6a7.png"},{"id":94457431,"identity":"61c6a723-cd25-4013-a05b-ad92eed5ab74","added_by":"auto","created_at":"2025-10-27 14:45:55","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28782,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinecrpcpu.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/3d6628e6c74d4e306084d574.png"},{"id":94457319,"identity":"b7640e3e-8df1-4cb8-977e-b8b737ff5197","added_by":"auto","created_at":"2025-10-27 14:45:41","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54660,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineframeworkllmcall.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/e584f800c454b3c9988b6837.png"},{"id":94457653,"identity":"7d057d86-85b7-4d79-93ff-8fef13615a99","added_by":"auto","created_at":"2025-10-27 14:46:07","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68505,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineinputprompt.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/2f255dc69462995446953979.png"},{"id":94457013,"identity":"73369289-255d-4f69-b3fe-a6cf834b4463","added_by":"auto","created_at":"2025-10-27 14:45:24","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20199,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineoth.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/a0203e00c3e40b68b057b387.png"},{"id":94457418,"identity":"a739d8ed-986d-4259-a7da-129f47dc3f1f","added_by":"auto","created_at":"2025-10-27 14:45:53","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14448,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineoutputprompt.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/267de2c272b9c3273f452f21.png"},{"id":94457317,"identity":"4e148c94-fac2-4ae7-a099-c249240280fa","added_by":"auto","created_at":"2025-10-27 14:45:41","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27608,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinerag.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/6ae24097cf6bb84e227cfbb3.png"},{"id":94457427,"identity":"383c32c4-8b91-4900-b8dc-2b287fdb16c5","added_by":"auto","created_at":"2025-10-27 14:45:54","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37332,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinetokenizersretrieval.png","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/507676b7227f2c12e969daff.png"},{"id":94489507,"identity":"94e074be-9890-450e-b35f-1b6892089ab7","added_by":"auto","created_at":"2025-10-27 17:04:56","extension":"xml","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102363,"visible":true,"origin":"","legend":"","description":"","filename":"7931305ae6f44c31896c09ac83383b031structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1/840ffbbd1b611384ed041715.xml"},{"id":106809298,"identity":"2c3ca7a1-2762-49e9-a818-26cbd172e06d","added_by":"auto","created_at":"2026-04-13 16:09:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":670885,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerJournal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7511605/v1_covered_cdc5b93b-5867-427b-959e-ee3cc7118161.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Leveraging Large Language Models for Document Classification in the Banking Sector","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":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Document Classification, Large Language Models, Banking Sector, Retrieval-Augmented Generation","lastPublishedDoi":"10.21203/rs.3.rs-7511605/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7511605/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Document classification serves as foundational step in critical tasks such as information extraction, analysis and decision-making. However, existing approaches often struggle with the variability, volume, and complexity of real-world documents. These methods are further limited by a lack of configurability and explainability, requiring specialized technical expertise to accommodate diverse user needs and often producing results that are difficult to interpret. To address the complexities of modern document processing, this paper introduces a novel zero-shot document classification framework that leverages Large Language Models (LLMs), designed for accessibility and configurability by both technical and non-technical users. Unlike traditional methods, which require extensive labeled data, the zero-shot configuration enables our framework to perform the classification task without any prior exposure to labeled examples of the target categories, relying instead on semantic understanding derived from user-provided label descriptions and document content. Developed and validated using a real-world banking dataset, our framework leverages different strategies for providing context to LLMs during classification. Experimental results demonstrate substantial improvements in both accuracy and efficiency, outperforming current zero-shot methods while also reducing operating costs.","manuscriptTitle":"Leveraging Large Language Models for Document Classification in the Banking Sector","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-27 11:43:06","doi":"10.21203/rs.3.rs-7511605/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-15T11:38:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-10T10:27:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-24T09:37:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-22T09:07:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"311935304684272425894958456726166468805","date":"2025-10-17T09:01:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"258356514331123991348466619540554348057","date":"2025-10-15T07:58:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"339985982586185417149999812871776642132","date":"2025-10-14T11:52:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-14T11:05:39+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-25T09:39:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-02T07:36:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Data Science and Analytics","date":"2025-09-01T21:24:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f60e91ac-1fc6-42c6-8ad9-fd0b943b4103","owner":[],"postedDate":"October 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-13T16:06:50+00:00","versionOfRecord":{"articleIdentity":"rs-7511605","link":"https://doi.org/10.1007/s41060-026-01077-x","journal":{"identity":"international-journal-of-data-science-and-analytics","isVorOnly":false,"title":"International Journal of Data Science and Analytics"},"publishedOn":"2026-04-06 15:58:37","publishedOnDateReadable":"April 6th, 2026"},"versionCreatedAt":"2025-10-27 11:43:06","video":"","vorDoi":"10.1007/s41060-026-01077-x","vorDoiUrl":"https://doi.org/10.1007/s41060-026-01077-x","workflowStages":[]},"version":"v1","identity":"rs-7511605","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7511605","identity":"rs-7511605","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.