PAGE-RAG: Evidence-Grounded Adaptive Graph Retrieval for Long-Document Question Answering
2026-07-21 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors study how to improve answering questions about very long documents by using graph-based structures that organize information. They point out that automatic graphs don't capture everything perfectly and shouldn't replace the original documents but rather help navigate them. Their system, PAGE-RAG, decides how to retrieve information based on the question and makes sure answers only use reliable, supported facts. Tests show that PAGE-RAG answers questions well while being more efficient and trustworthy.
long-document question answeringgraph retrievalknowledge graphprojection-aware modelingadaptive retrievalknowledge boundary controlinformation retrievalGraphRAG
Authors
Xingyu Chen, Junxiu An, Jun Guo, Li Wang
Abstract
GraphRAG improves long-document question answering by introducing structured representations beyond conventional retrieval. However, automatically constructed graphs are inherently incomplete projections of source documents, and treating them as independent knowledge sources may lead to unreliable retrieval and generation. We propose PAGE-RAG, a projection-aware adaptive graph retrieval framework for reliable long-document question answering. PAGE-RAG views graph structures as semantic skeletons that organize and navigate document knowledge, rather than replacing the original knowledge source. Based on this perspective, PAGE-RAG introduces a task-adaptive retrieval routing strategy that dynamically selects appropriate retrieval behaviors according to query requirements. Furthermore, PAGE-RAG incorporates strict knowledge boundary control, ensuring that generated responses remain grounded within available evidence and abstaining from unsupported information beyond the accessible knowledge scope. Experiments demonstrate that PAGE-RAG achieves competitive answer quality while improving retrieval efficiency and knowledge reliability, highlighting the importance of projection-aware graph modeling, adaptive retrieval, and explicit knowledge boundary control for trustworthy GraphRAG systems. The source code is publicly available at https://github.com/CXY0112/PAGE-RAG.