Enhancing Document-Level Question Answeringvia Multi-Hop Retrieval-Augmented Generationwith LLaMA 3

Enhancing Document-Level Question Answeringvia Multi-Hop Retrieval-Augmented Generationwith LLaMA 3 | 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 Enhancing Document-Level Question Answeringvia Multi-Hop Retrieval-Augmented Generationwith LLaMA 3 Xinyue Huang, Ziqi Lin, Fang Sun, Wenchao Zhang, Kejian Tong, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8296653/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 This paper presents a novel Retrieval-AugmentedGeneration (RAG) framework tailored for complex questionanswering tasks, addressing challenges in multi-hop reasoningand contextual understanding across lengthy documents. Builtupon LLaMA 3, the framework integrates a dense retrievalmodule with advanced context fusion and multi-hop reasoningmechanisms, enabling more accurate and coherent responsegeneration. A joint optimization strategy combining retrievallikelihood and generation cross-entropy improves the model’srobustness and adaptability. Experimental results show that theproposed system outperforms existing retrieval-augmented andgenerative baselines, confirming its effectiveness in deliveringprecise, contextually grounded answers. Artificial Intelligence and Machine Learning retrieval-augmented generation financial QA multi-hop reasoning LLaMA 3 context fusion artificial intelligence machine learning deep learning 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-8296653","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":556320233,"identity":"39048ad5-f007-4c58-997a-6aefdad6fb48","order_by":0,"name":"Xinyue Huang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIiWNgGAWjYBACAwglASIYH3wwsJEDsQ48IFILs+GMgjRjsJYEwlrAgE2a48OhxAYQE58Wc4nkZw+/tlnkGdxIPmzMYHAgfX7Y4YdAW+zkdBuwa7GckWZuLHNGotjgRlri4wKDO7kbb6cZALUkG5sdwOGwGwlm0hIVEokbbuQYG88weJa7cXYCSMuBxG04taR/k5YwAGnJ/ybNY3A43XB2+gcCWnLMJD9AbGEDaUmQl84hYMuZN2XSDGckEmeeeWZsOMMgzXCDdE7BgQQDPH45nr5N8mdbXWLf8eSHDz78sZGXn52++cOHCjs5XFpAgJkHSCjAFBiAGQa4FEMA4w8gId8A5cEZo2AUjIJRMAqgAAAef2q0gi0aiAAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Xinyue","middleName":"","lastName":"Huang","suffix":""},{"id":556320234,"identity":"6dfad6ae-97cc-4006-b1c1-6611c4bd44eb","order_by":1,"name":"Ziqi Lin","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ziqi","middleName":"","lastName":"Lin","suffix":""},{"id":556320235,"identity":"961db075-f217-4533-b31a-c2ab67e8a443","order_by":2,"name":"Fang Sun","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Fang","middleName":"","lastName":"Sun","suffix":""},{"id":556320236,"identity":"0a332cb4-e6ec-4f05-bfe7-59cad56ca386","order_by":3,"name":"Wenchao Zhang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Wenchao","middleName":"","lastName":"Zhang","suffix":""},{"id":556320237,"identity":"75cc7156-0f03-450c-8f89-8202d6ec3953","order_by":4,"name":"Kejian Tong","email":"","orcid":"https://orcid.org/0009-0002-5127-2711","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Kejian","middleName":"","lastName":"Tong","suffix":""},{"id":556320238,"identity":"f5f74a43-7119-414e-8ae7-9deca2c37f88","order_by":5,"name":"Yunbo Liu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yunbo","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-12-06 19:55:40","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-8296653/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8296653/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97896773,"identity":"52e4f72d-ef40-4473-a330-3f8c0bec3c19","added_by":"auto","created_at":"2025-12-10 15:37:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":969043,"visible":true,"origin":"","legend":"","description":"","filename":"EnhancingDocumentLevelQuestionAnsweringviaMultiHopRetrievalAugmentedGenerationwithLLaMA3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8296653/v1_covered_ed22aa3d-ffb8-4e76-9111-47e9f0ad4021.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEnhancing Document-Level Question Answeringvia Multi-Hop Retrieval-Augmented Generationwith LLaMA 3\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"N/A","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":"retrieval-augmented generation, financial QA, multi-hop reasoning, LLaMA 3, context fusion, artificial intelligence machine learning, deep learning","lastPublishedDoi":"10.21203/rs.3.rs-8296653/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8296653/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents a novel Retrieval-AugmentedGeneration (RAG) framework tailored for complex questionanswering tasks, addressing challenges in multi-hop reasoningand contextual understanding across lengthy documents. Builtupon LLaMA 3, the framework integrates a dense retrievalmodule with advanced context fusion and multi-hop reasoningmechanisms, enabling more accurate and coherent responsegeneration. A joint optimization strategy combining retrievallikelihood and generation cross-entropy improves the model’srobustness and adaptability. Experimental results show that theproposed system outperforms existing retrieval-augmented andgenerative baselines, confirming its effectiveness in deliveringprecise, contextually grounded answers.\u003c/p\u003e","manuscriptTitle":"Enhancing Document-Level Question Answeringvia Multi-Hop Retrieval-Augmented Generationwith LLaMA 3","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-09 04:09:20","doi":"10.21203/rs.3.rs-8296653/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":"6bd1f234-9159-426d-9a38-48d1bf66b7dd","owner":[],"postedDate":"December 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":59212965,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-12-09T04:09:20+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-09 04:09:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8296653","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8296653","identity":"rs-8296653","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}