LEDGE : Leveraging Dependency Graphs for Enhanced Context Aware Documentation Generation

LEDGE : Leveraging Dependency Graphs for Enhanced Context Aware Documentation Generation | 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 LEDGE : Leveraging Dependency Graphs for Enhanced Context Aware Documentation Generation Mihir Panchal, Arnav Deo, Varad Prabhu, Prinkal Doshi, Chetashri Bhadane, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6827966/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Feb, 2026 Read the published version in Automated Software Engineering → Version 1 posted 9 You are reading this latest preprint version Abstract In software engineering, effective documentation is crucial for understanding complex codebases, yet it often remains incomplete or outdated, hindering developer productivity. This paper introduces LEDGE (Leveraging Dependency Graphs for Enhanced Context Aware Documentation Generation), a novel framework that integrates dependency graphs with large language models (LLMs) to automate the generation of structured, context aware software documentation. By leveraging GraphRAG, LEDGE captures semantic and structural relationships within codebases, enabling precise documentation that highlights architectural insights and module dependencies. Our methodology employs a parser based approach to construct dependency graphs, stored in MemGraph using Cypher queries, and utilizes vector embeddings for similarity based retrieval. Evaluated on diverse open source repositories, LEDGE demonstrates superior clarity and relevance compared to traditional documentation, as evidenced by qualitative and quantitative analyses. The framework enhances software maintainability, developer onboarding, and knowledge transfer, offering a scalable solution for modern software development. Our code and data are available at https://github.com/MihirRajeshPanchal/LEDGE . Software Development Dependency Graphs Knowledge Graphs Source Code Analysis Automated Documentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Feb, 2026 Read the published version in Automated Software Engineering → Version 1 posted Editorial decision: Revision requested 12 Aug, 2025 Reviews received at journal 12 Aug, 2025 Reviews received at journal 09 Jul, 2025 Reviewers agreed at journal 08 Jul, 2025 Reviewers agreed at journal 29 Jun, 2025 Reviewers invited by journal 17 Jun, 2025 Editor assigned by journal 17 Jun, 2025 Submission checks completed at journal 09 Jun, 2025 First submitted to journal 05 Jun, 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-6827966","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":466936059,"identity":"1a25b02b-e0dd-4b7f-862c-76664277ce63","order_by":0,"name":"Mihir Panchal","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIiWNgGAWjYDACZh6GA2CGBAPj4R88Ejz8IE5CAXFaGA4zyNjISTaAtBjgs4YHSoO12KQZG4BNwKNFt5334OHKHXZ5/LObHxwuyDmcuPn86sQPDwwY5PnFDmDVYnaYL+Hg2TPJxRJ3jhkcnnHmcOK2G283SwAdZjhzdgIOLTwGBxvbmBM3AJUd4O0BaTkLYgO9cxuvlnqglvQPB3j/AR024+zmH0RoOQzUkmNwmIcH6H3+3m1E2HLmeOKMGzkFB2fw2MhJ3ODdZpFgIIHbL+fPGH9s3FGd2D8jfeODD6Co7D+7+eaPCht5fmnsWsCAsQGZJwFWKYFbOaYW/gP4VY+CUTAKRsGIAwC/QWwy87SzqAAAAABJRU5ErkJggg==","orcid":"","institution":"Dwarkadas J. Sanghvi College of Engineering","correspondingAuthor":true,"prefix":"","firstName":"Mihir","middleName":"","lastName":"Panchal","suffix":""},{"id":466936060,"identity":"e386a1cc-236e-4ad7-a01f-593436167765","order_by":1,"name":"Arnav Deo","email":"","orcid":"","institution":"Dwarkadas J. Sanghvi College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Arnav","middleName":"","lastName":"Deo","suffix":""},{"id":466936061,"identity":"169e9c29-a2f3-4111-832b-d831f629c3cd","order_by":2,"name":"Varad Prabhu","email":"","orcid":"","institution":"Dwarkadas J. Sanghvi College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Varad","middleName":"","lastName":"Prabhu","suffix":""},{"id":466936062,"identity":"cd6f66e5-50c6-469b-ad43-b8ff027b03ac","order_by":3,"name":"Prinkal Doshi","email":"","orcid":"","institution":"Dwarkadas J. Sanghvi College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Prinkal","middleName":"","lastName":"Doshi","suffix":""},{"id":466936063,"identity":"70cf166d-7fb1-416b-b76f-a79e8af38bae","order_by":4,"name":"Chetashri Bhadane","email":"","orcid":"","institution":"Dwarkadas J. Sanghvi College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Chetashri","middleName":"","lastName":"Bhadane","suffix":""},{"id":466936064,"identity":"7999d633-cbda-42b9-89fe-4549bb7baa3c","order_by":5,"name":"Pranit Bari","email":"","orcid":"","institution":"Dwarkadas J. Sanghvi College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Pranit","middleName":"","lastName":"Bari","suffix":""}],"badges":[],"createdAt":"2025-06-05 10:08:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6827966/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6827966/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10515-026-00596-y","type":"published","date":"2026-02-03T15:57:20+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":102234183,"identity":"1bc2e57f-1758-44a6-8fa5-8eb53de87fa8","added_by":"auto","created_at":"2026-02-09 16:07:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":678024,"visible":true,"origin":"","legend":"","description":"","filename":"LEDGE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6827966/v1_covered_4ee97766-0604-45db-b9da-8ee472231e80.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LEDGE : Leveraging Dependency Graphs for Enhanced Context Aware Documentation Generation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"automated-software-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ause","sideBox":"Learn more about [Automated Software Engineering](http://link.springer.com/journal/10515)","snPcode":"10515","submissionUrl":"https://submission.nature.com/new-submission/10515/3","title":"Automated Software Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Software Development, Dependency Graphs, Knowledge Graphs, Source Code Analysis, Automated Documentation","lastPublishedDoi":"10.21203/rs.3.rs-6827966/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6827966/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In software engineering, effective documentation is crucial for understanding complex codebases, yet it often remains incomplete or outdated, hindering developer productivity. This paper introduces LEDGE (Leveraging Dependency Graphs for Enhanced Context Aware Documentation Generation), a novel framework that integrates dependency graphs with large language models (LLMs) to automate the generation of structured, context aware software documentation. By leveraging GraphRAG, LEDGE captures semantic and structural relationships within codebases, enabling precise documentation that highlights architectural insights and module dependencies. Our methodology employs a parser based approach to construct dependency graphs, stored in MemGraph using Cypher queries, and utilizes vector embeddings for similarity based retrieval. Evaluated on diverse open source repositories, LEDGE demonstrates superior clarity and relevance compared to traditional documentation, as evidenced by qualitative and quantitative analyses. The framework enhances software maintainability, developer onboarding, and knowledge transfer, offering a scalable solution for modern software development. Our code and data are available at https://github.com/MihirRajeshPanchal/LEDGE.","manuscriptTitle":"LEDGE : Leveraging Dependency Graphs for Enhanced Context Aware Documentation Generation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-06 05:54:22","doi":"10.21203/rs.3.rs-6827966/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-12T16:25:48+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-12T06:59:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-09T14:46:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"117090044366862674964078354908687631709","date":"2025-07-08T18:47:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"19391878984674942170128969865758268037","date":"2025-06-29T14:12:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-17T13:17:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-17T07:05:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-09T11:48:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Automated Software Engineering","date":"2025-06-05T09:54:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"automated-software-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ause","sideBox":"Learn more about [Automated Software Engineering](http://link.springer.com/journal/10515)","snPcode":"10515","submissionUrl":"https://submission.nature.com/new-submission/10515/3","title":"Automated Software Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a20ef6ff-1ec1-4452-bff0-0897aadae536","owner":[],"postedDate":"June 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-09T16:03:28+00:00","versionOfRecord":{"articleIdentity":"rs-6827966","link":"https://doi.org/10.1007/s10515-026-00596-y","journal":{"identity":"automated-software-engineering","isVorOnly":false,"title":"Automated Software Engineering"},"publishedOn":"2026-02-03 15:57:20","publishedOnDateReadable":"February 3rd, 2026"},"versionCreatedAt":"2025-06-06 05:54:22","video":"","vorDoi":"10.1007/s10515-026-00596-y","vorDoiUrl":"https://doi.org/10.1007/s10515-026-00596-y","workflowStages":[]},"version":"v1","identity":"rs-6827966","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6827966","identity":"rs-6827966","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}