A Hybrid Retrieval-Augmented Generation and Language Model Framework for Evidence-Grounded Review Systems

A Hybrid Retrieval-Augmented Generation and Language Model Framework for Evidence-Grounded Review Systems | 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 A Hybrid Retrieval-Augmented Generation and Language Model Framework for Evidence-Grounded Review Systems Chidozie Managwu, Lanre Shittu, David Obi-Nwankpa This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7706204/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 Evidence-grounded review systems require balancing comprehensive knowledge retrieval with accurate and reliable generation. Traditional approaches often struggle with maintaining factual consistency, providing proper attribution, and combining complex multi-source evidence. In this study we propose a reliable hybrid framework that integrates retrieval-augmented generation with large language models to support evidence-grounded critiques, risk assessments, and recommendations. The framework created ensures to incorporate structured rubrics, a dual-model verification, and a human-in-the-loop to enforce and ensure quality control to produce reliable outputs across domains. Unlike prior systems such as Atlas and RETRO, the approach proposed in this research introduces explicit verification and calibration mechanisms that reduce factual errors and improve attribution. Empirical evaluations applied show visible and notable improvements in groundedness (91% vs. 71% baseline), consistency (89% vs. 63% baseline), and reliability (ECE 0.042, 47% lower than Atlas). Our approach uses a browser-based architecture which removes the need for specialised hardware, making the system more accessible. This work advances the development of trustworthy review systems and has broader implications for high-stakes fields such as healthcare, legal analysis, and policy evaluation. Artificial Intelligence and Machine Learning Software Engineering evidence-grounded review human-in-the-loop large language model (LLM) natural language inference retrieval-augmented generation (RAG) 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-7706204","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":520134659,"identity":"7368d0c8-0827-409e-9da6-c3232f9fd652","order_by":0,"name":"Chidozie Managwu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIiWNgGAWjYDACCcYGCSCJEOAHEQkFpGiRbABpMcCnBUU9EBgcAJO4dfDPbm688eGPhRyD2OFnD378Opy4+fzqxA8PDBjk+cUOYLfkzsFmyxk8EsYM0mnmhr19hxO33Xi7WQLoMMOZsxOwajGQSGyT5pGQSGyQTjCT4O25DdRydgNIS4LBbXxaDCTqG6TTv0n+BWrZPOPs5h+EtSRIJDBI55hJ8/y4nbiBv3cbXlskbiQC/XJAwrBNOqdMWrbhv/GMG7zbLBIMJHD6hX9G+kNgiNXJ80unb5N88ydNtr//7OabPypsgCLYtcABG4hgbANZDFYpgU8xMvgDsvgAsapHwSgYBaNghAAA9HNgLiXZqXwAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-4051-5503","institution":"University of Bradford","correspondingAuthor":true,"prefix":"","firstName":"Chidozie","middleName":"","lastName":"Managwu","suffix":""},{"id":520134783,"identity":"9752831b-2153-4caf-98ca-9362d8b5523c","order_by":1,"name":"Lanre Shittu","email":"","orcid":"","institution":"University of Bradford","correspondingAuthor":false,"prefix":"","firstName":"Lanre","middleName":"","lastName":"Shittu","suffix":""},{"id":520134784,"identity":"cd03f82a-e541-4b74-8d97-e9c519e1d407","order_by":2,"name":"David Obi-Nwankpa","email":"","orcid":"","institution":"University of Hull","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Obi-Nwankpa","suffix":""}],"badges":[],"createdAt":"2025-09-24 17:58:18","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-7706204/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7706204/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92220929,"identity":"6d7e7adc-430d-445a-b2a5-4485af72ed64","added_by":"auto","created_at":"2025-09-26 03:14:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":323530,"visible":true,"origin":"","legend":"","description":"","filename":"AHYBRIDRAGANDLLMFRAMEWORKFOREVIDENCEGROUNDEDREVIEWSYSTEMSRevised1121.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7706204/v1_covered_0f53d0fe-dd1f-49fb-8e71-26971a1f82fd.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eA Hybrid Retrieval-Augmented Generation and Language Model Framework for Evidence-Grounded Review Systems\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Bradford","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":"evidence-grounded review, human-in-the-loop, large language model (LLM), natural language inference, retrieval-augmented generation (RAG) ","lastPublishedDoi":"10.21203/rs.3.rs-7706204/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7706204/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEvidence-grounded review systems require balancing comprehensive knowledge retrieval with accurate and reliable generation. Traditional approaches often struggle with maintaining factual consistency, providing proper attribution, and combining complex multi-source evidence. In this study we propose a reliable hybrid framework that integrates retrieval-augmented generation with large language models to support evidence-grounded critiques, risk assessments, and recommendations. The framework created ensures to incorporate structured rubrics, a dual-model verification, and a human-in-the-loop to enforce and ensure quality control to produce reliable outputs across domains. Unlike prior systems such as Atlas and RETRO, the approach proposed in this research introduces explicit verification and calibration mechanisms that reduce factual errors and improve attribution. Empirical evaluations applied show visible and notable improvements in groundedness (91% vs. 71% baseline), consistency (89% vs. 63% baseline), and reliability (ECE 0.042, 47% lower than Atlas). Our approach uses a browser-based architecture which removes the need for specialised hardware, making the system more accessible. This work advances the development of trustworthy review systems and has broader implications for high-stakes fields such as healthcare, legal analysis, and policy evaluation.\u003c/p\u003e","manuscriptTitle":"A Hybrid Retrieval-Augmented Generation and Language Model Framework for Evidence-Grounded Review Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-26 03:06:11","doi":"10.21203/rs.3.rs-7706204/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":"a4c6cadb-5a1c-41bf-b8b5-cb26f2fae5d4","owner":[],"postedDate":"September 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55287818,"name":"Artificial Intelligence and Machine Learning"},{"id":55287819,"name":"Software Engineering"}],"tags":[],"updatedAt":"2025-09-26T03:06:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-26 03:06:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7706204","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7706204","identity":"rs-7706204","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}