[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-665443-105":59,"doc-detail-665443-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","query2diagram-answering-developer-queries-with-uml-diagrams","Query2Diagram - Answering Developer Queries with UML Diagrams","","Software documentation and UML diagrams often become outdated or disappear entirely, yet developers require precise, focused views of complex codebases. Automated reverse-engineering can generate diagrams, but typically overwhelms readers by ignoring developer intent and question context. This work proposes query-driven UML generation, using LLMs to produce semantically relevant diagrams that include only pertinent elements with contextual descriptions. Fine-tuning Qwen2.5-Coder-14B on curated code-query-diagram JSON data improves F1 scores and lowers structural defect rates, enabling scalable on-demand documentation.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/query2diagram-answering-developer-queries-with-uml-diagrams/665443/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/query2diagram-answering-developer-queries-with-uml-diagrams/665443.png","ImageObject",300,407,{"name":92,"@type":93},"Miles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-29",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does Query2Diagram address?","Question",{"text":112,"@type":113},"Software UML documentation often becomes missing or diverges from implementation. Reverse-engineering tools can generate diagrams but may include overwhelming details that reduce comprehension.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does Query2Diagram generate UML diagrams for developer questions?",{"text":117,"@type":113},"It uses LLMs to generate UML diagrams directly from natural-language queries about code, producing diagrams focused on only relevant elements with contextual descriptions.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the model trained and evaluated?",{"text":121,"@type":113},"The work fine-tunes Qwen2.5-Coder-14B on a curated dataset of code files, developer queries, and structured JSON diagram representations. Evaluation combines automatic structural defect detection with human semantic relevance assessment.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},665443,1793304176,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":46,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":31},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","arXiv :2604 .238 16v2 [ cs . SE] 5 Jul 2026  \nQuery2Diagram: Answering Developer Queries  \nwith UML Diagrams∗  \nOleg Baryshnikov  \nHSE University  \n[baryshnikovod@gmail.com](baryshnikovod@gmail.com)  \nAnton M. Alekseev  \nSt. Petersburg Department ofSteklov Mathematical Institute, RAS,  \nSt. Petersburg State University  \n[anton.m.alexeyev@gmail.com](anton.m.alexeyev@gmail.com)  \nSergey I. Nikolenko  \nSt. Petersburg Department ofSteklov Mathematical Institute, RAS,  \nSt. Petersburg State University  \n[sergey@logic.pdmi.ras.ru](sergey@logic.pdmi.ras.ru)  \nAbstract  \nSoftware documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems. While automated reverse engineering tools can generate UML diagrams from code, they produce overwhelming detail without considering developer intent. We introduce query-driven UML diagram generation, where LLMs create diagrams that directly answer natural language questions about code. Unlike existing methods, our approach produces semantically focused diagrams containing only relevant elements with contextual descriptions. We fine-tune Qwen2.5-Coder-14B on a curated dataset of code files, developer queries, and corresponding diagram representations in a structured JSON format, evaluating with both automatic detection of structural defects and human assessment of semantic relevance. Results demonstrate that fine-tuning on a modest amount of manually corrected data yields dramatic improvements: our best model achieves the highest F1 scores while reducing defect rates below state-of-the-art LLMs, generating diagrams that are both structurally sound and semantically faithful to developer queries. Thus, we establish the feasibility of using LLMs for scalable contextual, on-demand documentation generation. We make our code and dataset publicly available at [https://github.com/i-need-a-pencil/query2diagram](https://github.com/i-need-a-pencil/query2diagram).  \nKeywords: Large Language Models · Code QA · UML · Documentation Maintenance.  \n1 Introduction  \nSoftware documentation, particularly UML diagrams, plays a crucial role in system comprehension and maintenance. Studies confirm that UML usage improves code quality and  \n∗ Submitted to the Journal of Mathematical Sciences.  \nFigure 1: A sample response to the user query “Map out the event listeners set up in the CRServiceWorker constructor and their corresponding actions” based on the TypeScript file microsoft/playwright/ ... /crServiceWorker.ts.  \nmodularity, reduces defects, and increases developer productivity [3, 29–31] . However, manually creating and, crucially, maintaining up-to-date diagrams requires significant effort, leading to a common problem: documentation that either does not exist or diverges from the actual implementation [20] .  \nIn the absence of up-to-date UML documentation, diagrams can be generated with automated reverse-engineering (RE) tools. However, the resulting UML diagrams often contain overwhelming detail that hinders comprehension; studies and developer surveys show that these diagrams have tobe severely simplified for clarity [32,33] . Some approaches propose interactive filtering mechanisms [12], but typically ignore semantic context and user intent. This creates a gap: developers need focused, contextual views of their codebase, not exhaustive structural dumps.  \nRecent advances in NLP, specifically large language models (LLMs), offer a promising solution. LLMs excel at understanding both code and natural language, making them uniquely suited to bridge the gap between developer queries and visual representations. Although LLM applications in software engineering are expanding rapidly [28, 46], including tools such as GitHub Copilot [41] and Cursor [42], their potential for query-driven diagram generation remains unexplored.  \nMotivated by this gap, we present a novel approach: using LLMs to generate RE-UML diagrams that directly a","cbCailw8c9z7sYk1","https://ap.wps.com/l/cbCailw8c9z7sYk1","pdf",780300,"English","# Introduction\n## Problem: outdated and overly detailed UML documentation\n## Gap: lack of semantic context and developer intent\n## Proposed approach: query-driven UML generation with LLMs\n## Research questions and contributions","[{\"question\":\"What problem does Query2Diagram address?\",\"answer\":\"Software UML documentation often becomes missing or diverges from implementation. Reverse-engineering tools can generate diagrams but may include overwhelming details that reduce comprehension.\"},{\"question\":\"How does Query2Diagram generate UML diagrams for developer questions?\",\"answer\":\"It uses LLMs to generate UML diagrams directly from natural-language queries about code, producing diagrams focused on only relevant elements with contextual descriptions.\"},{\"question\":\"How is the model trained and evaluated?\",\"answer\":\"The work fine-tunes Qwen2.5-Coder-14B on a curated dataset of code files, developer queries, and structured JSON diagram representations. Evaluation combines automatic structural defect detection with human semantic relevance assessment.\"}]","Query2Diagram - Answering Developer Queries with UML Diagrams | PDF"]