{"paper_id":"35056694-6ca7-4044-a1e6-e75b9051007f","body_text":"RAG-KED Summarization: A Framework for Knowledge-Augmented Article Summarization with Large Language Models | 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 RAG-KED Summarization: A Framework for Knowledge-Augmented Article Summarization with Large Language Models Abdulrehman Mohsen Ahmed Zeyad, Arun Biradar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7975001/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 study introduces the RAG-KED framework, a novel approach designed to enhance the accuracy and relevance of scientific article summaries by integrating Retrieval-Augmented Generation (RAG) and Knowledge Example-Driven (KED) summarization. The primary objective is to address the limitations of traditional large language models (LLMs) in handling knowledge-intensive tasks, particularly in dynamic fields like biomedical research, where static training data quickly becomes outdated. The methodology leverages retrieval mechanisms to access current, do-main-specific information and employs curated example analyses to guide the structure and content of summaries. Evaluation was conducted using the eLife dataset, assessing advanced models such as Llama-3.2-90b, Llama-3.1-70b, and GPT-4o Mini. Key results demonstrate that models incorporating sample summaries significantly outper-form those without, as evidenced by higher ROUGE and BLEU + scores. Specifically, Llama-3.2-90b achieves the highest performance among tested models when guided by samples, while GPT-4o Mini excels across multiple met-rics. The study concludes that the RAG-KED framework markedly improves summary quality, thereby enhancing the accessibility of complex scientific knowledge. These findings underscore the framework’s potential to bridge critical gaps in domain-specific summarization, although its effectiveness hinges on the robustness of retrieval mechanisms and the quality of example summaries. Artificial Intelligence and Machine Learning Information Retrieval and Management Knowledge Example-Driven (KED) Summarization Retrieval-Augmented Generation (RAG) Article Summarization Large Language Models (LLMs) eLife dataset Evaluation Metrics (ROUGE BLEU+) 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-7975001\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":536612332,\"identity\":\"a2fe733d-a987-495c-b6a7-9bf685c8ae36\",\"order_by\":0,\"name\":\"Abdulrehman Mohsen Ahmed Zeyad\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYDCCAzDG8QYgYWBBipYzIJaBBClabiSASCK08N0+/HTjj4rD8nw3n1/d8KNAgoG/vTsBrxbJc2lmNyTOHDaceTun7GYP0GESZ85uwKvF4AyD2Q3DtsOMG27npN3gAWoxkMglpIX9243Ef4ftN9w8k3bzD3FaeMxuHGw4nLjhBvux20TZInmGp+xmw7H05JlncthuyxhI8BD0C98Z9m03f9RY2/YdP/7s5ps/NnL87b34tUBBMxDzGIBYPMQoB4E6IGZ/QKzqUTAKRsEoGGEAANkjUyj1lpteAAAAAElFTkSuQmCC\",\"orcid\":\"https://orcid.org/0009-0005-1725-2188\",\"institution\":\"REVA University, Bangalore, India.\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Abdulrehman\",\"middleName\":\"Mohsen Ahmed\",\"lastName\":\"Zeyad\",\"suffix\":\"\"},{\"id\":536612333,\"identity\":\"06f3b5bd-2a98-4fe6-8ec1-c23c563fdcbe\",\"order_by\":1,\"name\":\"Arun Biradar\",\"email\":\"\",\"orcid\":\"https://orcid.org/0000-0003-2355-7066\",\"institution\":\"REVA University, Bangalore, India.\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Arun\",\"middleName\":\"\",\"lastName\":\"Biradar\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-10-29 03:36:11\",\"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-7975001/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7975001/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":94724482,\"identity\":\"90e13e98-0ac1-4f85-a441-251c75c3bf00\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 06:15:11\",\"extension\":\"docx\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":516981,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"IJDSAv1.docx\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/9be79e5dd95b003614cfb30d.docx\"},{\"id\":94724481,\"identity\":\"069f097c-d9a3-49ef-befd-44471c1af545\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 06:15:11\",\"extension\":\"json\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":342,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs7975001.json\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/379c309f231a5d1d929e7988.json\"},{\"id\":94724487,\"identity\":\"38cdb43b-55a2-4ced-93bc-069c4115a981\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 06:15:11\",\"extension\":\"xml\",\"order_by\":2,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":143543,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs79750010enriched.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/091f3c4d72d24851a17173a3.xml\"},{\"id\":94724483,\"identity\":\"430ae4f3-3ba1-4d02-af4a-88b531781321\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 06:15:11\",\"extension\":\"png\",\"order_by\":3,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":162071,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/8519a286d40d9a7148dae7f3.png\"},{\"id\":94730151,\"identity\":\"88c98023-7327-413b-978b-6f84235bf6c9\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 07:05:42\",\"extension\":\"png\",\"order_by\":4,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":109708,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/78523379fc652ad7a81bd120.png\"},{\"id\":94724485,\"identity\":\"ab205e7d-e95e-4393-9530-11bbd495066c\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 06:15:11\",\"extension\":\"png\",\"order_by\":5,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":109942,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/45bc60e2461e375cc76ec430.png\"},{\"id\":94730204,\"identity\":\"f480783f-fe64-4a58-89f9-c0460583fe2c\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 07:05:46\",\"extension\":\"png\",\"order_by\":6,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":34358,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/a8e41eab65dc6538bc5afe02.png\"},{\"id\":94724489,\"identity\":\"9afbf47b-54a6-4667-a929-7af8aa041744\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 06:15:11\",\"extension\":\"png\",\"order_by\":7,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":115034,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/a4f495e238633d350a7a8cf9.png\"},{\"id\":94730130,\"identity\":\"1d8dd256-1a34-41c1-98c9-9973154e18c6\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 07:05:41\",\"extension\":\"png\",\"order_by\":8,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":112528,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/d0a094f78f537cd2e89e930e.png\"},{\"id\":94724488,\"identity\":\"f53701ef-3642-44ca-90b6-d0b5f4bce1fb\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 06:15:11\",\"extension\":\"xml\",\"order_by\":9,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":142589,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs79750010structuring.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/87dcf686f75cdaaa22261c64.xml\"},{\"id\":94730183,\"identity\":\"4756466d-bbb1-438a-8570-ae934bd19418\",\"added_by\":\"auto\",\"created_at\":\"2025-10-30 07:05:45\",\"extension\":\"html\",\"order_by\":10,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":158614,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"earlyproof.html\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1/fc45a7fcf0a38e141891ae8c.html\"},{\"id\":94822812,\"identity\":\"ae3ec010-0876-4036-8c2c-4056b7561b24\",\"added_by\":\"auto\",\"created_at\":\"2025-10-31 06:44:19\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":1037473,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"IJDSAv1.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7975001/v1_covered_0414cd12-5b51-435e-b114-071f90c94f62.pdf\"}],\"financialInterests\":\"The authors declare no competing interests.\",\"formattedTitle\":\"\\u003cp\\u003eRAG-KED Summarization: A Framework for Knowledge-Augmented Article Summarization with Large Language Models\\u003c/p\\u003e\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":true,\"hideJournal\":true,\"highlight\":\"\",\"institution\":\"REVA University\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"Knowledge Example-Driven (KED) Summarization, Retrieval-Augmented Generation (RAG), Article Summarization, Large Language Models (LLMs), eLife dataset, Evaluation Metrics (ROUGE, BLEU+)\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-7975001/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7975001/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eThis study introduces the RAG-KED framework, a novel approach designed to enhance the accuracy and relevance of scientific article summaries by integrating Retrieval-Augmented Generation (RAG) and Knowledge Example-Driven (KED) summarization. The primary objective is to address the limitations of traditional large language models (LLMs) in handling knowledge-intensive tasks, particularly in dynamic fields like biomedical research, where static training data quickly becomes outdated. The methodology leverages retrieval mechanisms to access current, do-main-specific information and employs curated example analyses to guide the structure and content of summaries. Evaluation was conducted using the eLife dataset, assessing advanced models such as Llama-3.2-90b, Llama-3.1-70b, and GPT-4o Mini. Key results demonstrate that models incorporating sample summaries significantly outper-form those without, as evidenced by higher ROUGE and BLEU\\u0026thinsp;+\\u0026thinsp;scores. Specifically, Llama-3.2-90b achieves the highest performance among tested models when guided by samples, while GPT-4o Mini excels across multiple met-rics. The study concludes that the RAG-KED framework markedly improves summary quality, thereby enhancing the accessibility of complex scientific knowledge. These findings underscore the framework\\u0026rsquo;s potential to bridge critical gaps in domain-specific summarization, although its effectiveness hinges on the robustness of retrieval mechanisms and the quality of example summaries.\\u003c/p\\u003e\",\"manuscriptTitle\":\"RAG-KED Summarization: A Framework for Knowledge-Augmented Article Summarization with Large Language Models\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-10-30 06:15:07\",\"doi\":\"10.21203/rs.3.rs-7975001/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"070f8d82-d15c-418b-ba9f-9674886d2b7b\",\"owner\":[],\"postedDate\":\"October 30th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[{\"id\":57057277,\"name\":\"Artificial Intelligence and Machine Learning\"},{\"id\":57057278,\"name\":\"Information Retrieval and Management\"}],\"tags\":[],\"updatedAt\":\"2025-10-30T06:15:07+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-10-30 06:15:07\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7975001\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7975001\",\"identity\":\"rs-7975001\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}