PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs

2026-07-09

AI Summary

This work addresses a critical limitation in current web-based Retrieval-Augmented Generation (RAG) systems, which largely ignore the semantic and hierarchical information embedded in HTML structures, resulting in responses that lack verifiability and structural awareness. To overcome this, the authors propose a novel heterogeneous graph framework that unifies the modeling of webpage DOM trees, inter-page hyperlinks, and cross-page entity relationships for the first time. They further introduce a two-tier, structure-aware routing mechanism that dynamically selects among three retrieval modes based on query requirements. The approach enables multi-hop graph traversal and generates traceable citations, significantly outperforming existing RAG systems on a PolyU official website dataset. It achieves superior performance in answer correctness, coverage, and faithfulness while substantially reducing LLM token consumption per query.

Abstract

Existing retrieval-augmented generation (RAG) systems treat web pages 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.

Problem

• retrieval-augmented generation
• web structure
• heterogeneous graph
• verifiable QA
• HTML semantics

Innovation

• structure-aware RAG
• heterogeneous graph
• verifiable QA
• DOM hierarchy
• multi-hop entity reasoning