[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85067-en":3,"doc-seo-85067-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85067,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","PolyUQuest Verifiable Structure Aware Web RAG over Heterogeneous Graphs","PolyUQuest presents a verifiable, structure-aware retrieval-augmented generation framework for web question answering where HTML is treated as layered signals rather than flat text. It builds a heterogeneous graph that merges hyperlink topology, DOM hierarchy, and cross-page entity–relation knowledge, and uses a two-tier router to select among block retrieval, cross-page traversal, and multi-hop entity reasoning. Citations are provenance-rich with page, heading path, and entity links. Evaluations on PolyU’s official site show improved correctness, coverage, faithfulness, and lower LLM token usage, plus an interactive demo interface.","PolyUQuest: Verifiable Structure-Aware Web RAG over  \nHeterogeneous Graphs  \nYing Liu, Yi Ye, Quanyu Feng, Mingxi Ye, Mingtao Zhang, Haoyang Li*, Chen Jason Zhang, Qing Li The Hong Kong Polytechnic University, Hong Kong SAR, China {yarden.liu, [yi000.ye](yi000.ye) , quanyu .feng, [mingxi.ye](mingxi.ye) , [mingtao.zhang}@connect.polyu.hk](mingtao.zhang}@connect.polyu.hk)[ ](mingtao.zhang}@connect.polyu.hk){ [haoyang-comp.li](haoyang-comp.li) , jason-c .zhang, [qing-prof.li}@polyu.edu.hk](qing-prof.li}@polyu.edu.hk)  \narXiv :2607 .08269v 1 [ cs .AI] 9 Jul 2026  \nAbstract  \nExisting retrieval-augmented generation (RAG) systems treat webpages as flat text, losing the structural and semantic signals encoded in HTML. We present PolyUQuest, a verifiable, structure-aware web RAG framework built on a heterogeneous graph that unifies hyperlink topology between pages, DOM hierarchy within pages, and entity–relation knowledge across pages. A two-tier router dispatches each query to one of three retrieval modes matched to its structural need, including direct block retrieval, cross-page graph traversal, and multi-hop entity reasoning. Every answer is fully verifiable, as each cited block carries its source page, heading path, and entity links so that users can trace any claim back to its structural evidence. We evaluate on the official websites of the Hong Kong Polytechnic University (PolyU), comprising 4,240 pages, 31,086 DOM blocks, 29,119 entities, and 37,680 relations, together with a multi-type evaluation benchmark. PolyUQuest outperforms existing RAG systems in answer correctness, coverage, and faithfulness, while consuming significantly fewer LLM tokens per query. The demonstration provides an interactive interface for inspecting cited answers, comparing retrieval traces across routing modes, and exploring evidence graph paths. PolyUQuest is being prepared for deployment as a student-facing QA service at PolyU. A demo video is available at [https://youtu.be/thKWYaL_4rw](https://youtu.be/thKWYaL_4rw).  \nKeywords  \nRetrieval Augmented Generation, Question Answering, Heterogeneous Graphs, Web Search  \n1 Introduction  \nWeb pages are among the most widely used knowledge sources for retrieval-augmented generation (RAG) [10, 16, 25], where retrieving accurate and current evidence is key to curbing hallucination [4, 11, 27, 31] . Unlike plain documents, web content is organized in three complementary layers: hyperlinks between pages, a DOM hierarchy within each page, and named entities that recur across pages. Consider a prospective student asking,“Which professors in the Department of Computing conduct NLP research and also teach related courses?” No single page holds the answer: it is scattered across faculty profiles and course pages. Answering it requires following hyperlinks and connecting entities across pages, beyond the reach of plain similarity retrieval.  \nExisting RAG approaches cannot handle questions over structurally complex websites, especially those that require cross-page navigation. Plain-text and chunk-based RAG [15, 21] flattens each page into a bag of chunks and retrieves by similarity, discarding  \n∗ Corresponding author.  \nstructure entirely, while agentic web search can recover it by browsing, only at prohibitive token cost and latency. Graph RAG systems [5, 8, 17, 23, 24], such as LightRAG [5], instead capture entityrelation structure [19], yet they still flatten HTML into text and inject large global contexts that inflate the cost of every query [12, 32] . HTML-and document-structure-aware RAG [13, 18, 22], such as HtmlRAG [22], in contrast, preserves structure within a page or documents, but ignores the hyperlinks that connect pages and so cannot follow evidence across a site. In summary, existing systems fail to reason over hyperlink topology, DOM hierarchy, and crosspage entities together, and those closest to structure-awareness pay heavily in tokens and latency.  \nPolyUQuest (Section 2). In response, we have d","cbCaivf1byxaJxz4","https://ap.wps.com/l/cbCaivf1byxaJxz4","pdf",1384752,2,1,5,"English","en",105,"# Introduction\n## Three-layer web graph\n## Structure-driven retrieval\n## Verifiable answer provenance\n# Demonstration","[{\"question\":\"What web structures does PolyUQuest use to improve RAG over webpages?\",\"answer\":\"PolyUQuest unifies three structural layers: hyperlink topology across pages, DOM hierarchy within pages, and cross-page entity–relation knowledge in a heterogeneous graph.\"},{\"question\":\"How does PolyUQuest decide which retrieval mode to use for a query?\",\"answer\":\"A two-tier router dispatches each query to a retrieval mode matched to its structural needs: direct block retrieval for single-hop facts, cross-page navigation for comparison/aggregation, or multi-hop entity reasoning for evidence spread across pages.\"},{\"question\":\"How is an answer verifiable in PolyUQuest?\",\"answer\":\"Each cited block includes its source page, heading path, and entity links, enabling users to trace every claim back to the structural evidence shown in the interface.\"}]",1784200769,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"polyuquest-verifiable-structure-aware-web-rag-over-heterogeneous-graphs","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/polyuquest-verifiable-structure-aware-web-rag-over-heterogeneous-graphs/85067/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-18","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 web structures does PolyUQuest use to improve RAG over webpages?","Question",{"text":75,"@type":76},"PolyUQuest unifies three structural layers: hyperlink topology across pages, DOM hierarchy within pages, and cross-page entity–relation knowledge in a heterogeneous graph.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does PolyUQuest decide which retrieval mode to use for a query?",{"text":80,"@type":76},"A two-tier router dispatches each query to a retrieval mode matched to its structural needs: direct block retrieval for single-hop facts, cross-page navigation for comparison/aggregation, or multi-hop entity reasoning for evidence spread across pages.",{"name":82,"@type":73,"acceptedAnswer":83},"How is an answer verifiable in PolyUQuest?",{"text":84,"@type":76},"Each cited block includes its source page, heading path, and entity links, enabling users to trace every claim back to the structural evidence shown in the interface.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":22,"slug":137},19,"General","general"]