Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Hongwei Zhang, Xiaoman Wang, Zehui Ling, Ruicheng Zhu, Yue Zhang, Pinlong Cai, Fuke Shen, Botian Shi, Tongquan Wei, Guohang Yan• 2026

Related benchmarks

TaskDatasetResultRank
RetrievalLongDocURL
Recall76.36
30
Document Question AnsweringMMLongBench-Doc (test)
Accuracy49.09
16
Document Question AnsweringLongDocURL (test)
Accuracy55.52
16
Evidence-page retrievalMMLongBench-Doc
Recall75.68
12
Document Question AnsweringUDA PaperTab
Accuracy40.71
6
Document Question AnsweringUDA FetaTab
Accuracy66.63
6
Showing 6 of 6 rows

Other info

Follow for update