[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86494-en":3,"doc-seo-86494-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},86494,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",6,"Technology","Question Answering for Diagram-Rich Technical Meeting Videos","Software engineering increasingly depends on asynchronous communication artifacts, especially recorded technical meetings where stakeholders discuss concerns, rationale, and decisions. Such meetings frequently include diagram-based representations spanning requirements, system behavior, component interactions, and trace dependencies. Building reliable knowledge access is hard because evidence is scattered across speech, slides, and technical diagrams. The paper presents LMVQA, an LLM-based multimodal question-answering system that grounds answers in aligned audio-visual evidence and explicitly handles diagram-rich content.","Question Answering for Diagram-Rich Technical Meeting Videos  \nZhuoran Xu∗†, Jia Li∗†, Dayuan Tan†, Mark Cole†, Ish Ashraf†, Sandeep Puri†, Mehrdad Sabetzadeh∗, Shiva Nejati∗  \n∗ University of Ottawa, Ottawa, ON, Canada  \n†Ciena Corp, Ottawa, ON, Canada  \n{zxu045, jli714, m.sabetzadeh, [snejati](snejati}@uottawa.ca)[}](snejati}@uottawa.ca)[@uottawa.ca](snejati}@uottawa.ca)[ ](snejati}@uottawa.ca){datan, mcole, iashraf, [spuri](spuri}@ciena.com)[}](spuri}@ciena.com)[@ciena.com](spuri}@ciena.com)  \narXiv :2607 . 10494v 1 [ cs . SE] 11 Jul 2026  \nAbstract—Software engineering increasingly relies on asynchronous communication artifacts, including recorded meetings where stakeholders discuss concerns, rationale, and decisions. These meetings often include diagram-based representations of requirements, system behavior, component interactions, and trace dependencies. Accessing knowledge from these meetings is challenging because recordings are long and relevant evidence is distributed across speech, slides, and technical diagrams. This paper reports our industrial experience developing and evaluating LMVQA, an LLM-based multimodal question-answering system for technical meeting videos. Developed in collaboration with engineers at Ciena, LMVQA supports the understanding of requirements and design intent by grounding answers in audio and visual evidence, with explicit handling of diagram-rich content such as requirements and UML diagrams. It processes each video once to build a reusable time-stamped evidence corpus for grounded question answering. Across a Ciena dataset anda public dataset, we show that LMVQA significantly improves answer accuracy compared to a state-of-the-art baseline, from 31% to 94% on the Ciena dataset and from 21% to 88% on the public dataset, with larger gains on diagram-rich videos. We further show that, after one-time indexing, LMVQA reduces average response time from 81.3s to 3.3s on Ciena and from 98.4sto 9.2s on the public dataset, while lowering average token-based LLM API cost by about 75%. Finally, our interviews with three domain experts show that engineers particularly value LMVQA for locating software-engineering-relevant information, revisiting rationale, and tracing answers to specific video segments.  \nIndex Terms—Multimodal Question Answering, Large Language Models, Software Requirements and Design Diagrams  \nI. INTRODUCTION  \nA shared understanding of system goals, assumptions, constraints, design decisions, and rationale is essential to successful software projects [1] . Misalignment among stakeholders can create conflicting interpretations of requirements and design decisions, reducing efficiency and increasing project risk [2] . This challenge is amplified in industrial settings, where distributed stakeholders cannot always participate in synchronous discussions. As a result, asynchronous communication has become increasingly important in software engineering [3] .  \nRecorded technical meetings are one such medium [4] . They often capture requirements- and design-relevant information, including stakeholder concerns, rationale, decisions, dependencies, and visual explanations of system behavior,  \narchitecture, workflows, and design alternatives. Engineers revisit these videos to clarify requirements, recover decision rationale, and understand component dependencies. These activities are central to software maintenance and evolution, where engineers must frequently retrieve historical context, rationale, and architectural knowledge from prior technical discussions. Prior work shows that recorded video supports knowledge transfer when synchronous participation is not possible [5], [6] . However, these recordings are difficult to use efficiently because they are long, users often have specific questions, and relevant evidence is distributed across speech, slides, and technical diagrams.  \nThis challenge is especially important for software-intensive systems because technical meeting videos are hi","cbCaioxpfQslplB2","https://ap.wps.com/l/cbCaioxpfQslplB2","pdf",344428,1,12,"English","en",105,"# Introduction\n## Motivation\n## Challenges in Diagram-Rich Video QA\n## Proposed Approach","[{\"question\":\"What problem does LMVQA address in software engineering meetings?\",\"answer\":\"LMVQA addresses difficulty accessing knowledge from long technical meeting recordings where relevant evidence is split across speech, slides, and technical diagrams.\"},{\"question\":\"How does LMVQA ground answers when diagrams are present?\",\"answer\":\"LMVQA builds a reusable, time-stamped evidence corpus by processing video visual and audio streams, grounding responses in audio-visual evidence and using explicit handling for diagram-rich content such as requirements and UML diagrams.\"},{\"question\":\"What improvements does LMVQA achieve over a baseline?\",\"answer\":\"Across a Ciena dataset and a public dataset, LMVQA raises answer accuracy substantially (from 31% to 94% on Ciena, and from 21% to 88% on the public dataset), with larger gains for diagram-rich videos.\"}]",1784212155,30,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"question-answering-for-diagram-rich-technical-meeting-videos","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/question-answering-for-diagram-rich-technical-meeting-videos/86494/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does LMVQA address in software engineering meetings?","Question",{"text":75,"@type":76},"LMVQA addresses difficulty accessing knowledge from long technical meeting recordings where relevant evidence is split across speech, slides, and technical diagrams.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does LMVQA ground answers when diagrams are present?",{"text":80,"@type":76},"LMVQA builds a reusable, time-stamped evidence corpus by processing video visual and audio streams, grounding responses in audio-visual evidence and using explicit handling for diagram-rich content such as requirements and UML diagrams.",{"name":82,"@type":73,"acceptedAnswer":83},"What improvements does LMVQA achieve over a baseline?",{"text":84,"@type":76},"Across a Ciena dataset and a public dataset, LMVQA raises answer accuracy substantially (from 31% to 94% on Ciena, and from 21% to 88% on the public dataset), with larger gains for diagram-rich videos.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":28,"slug":121},8,"Research & Report","research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]