EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
About
Retrieving evidence pages from visually rich long documents is a key challenge in document question answering. Existing page-level visual retrievers operate under an independent matching paradigm: each page is scored in isolation based on query-page similarity. This paradigm can under-rank evidence pages whose signals are localized in fine-grained chunks or depend on document-internal associations. We propose EviProp, a retrieval method that recovers such pages via seeded relevance diffusion. EviProp models each document as a multimodal Chunk-Page graph with hierarchical, sequential, and similarity links. Given a query, it combines dense visual page priors with sparse chunk seeds, then runs Personalized PageRank to diffuse relevance over the graph. Experiments on MMLongBench-Doc and LongDocURL show consistent gains in evidence-page retrieval over independent visual retrieval and text-visual fusion baselines. Downstream QA results further show that improved retrieval translates into better answer accuracy, with negligible online retrieval overhead. Our code is released at https://github.com/Flyecnu/EviProp.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Retrieval | LongDocURL | Recall76.36 | 30 | |
| Document Question Answering | MMLongBench-Doc (test) | Accuracy49.09 | 16 | |
| Document Question Answering | LongDocURL (test) | Accuracy55.52 | 16 | |
| Evidence-page retrieval | MMLongBench-Doc | Recall75.68 | 12 | |
| Document Question Answering | UDA PaperTab | Accuracy40.71 | 6 | |
| Document Question Answering | UDA FetaTab | Accuracy66.63 | 6 |