# HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering Source: [HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering]() Collection index: [llms.txt]() Data updated: 2026-05-30T05:00:11.986Z Authors: Joongmin Shin, Gyuho Shim, Jeongbae Park, Jaehyung Seo, Heuiseok Lim Published: 2026-05-28T08:42:21.000Z ## Abstract Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in locating the correct document and evidence fragmentation in integrating scattered information. Existing approaches relying on flat text chunks or page-level images inherently struggle to (i) precisely pinpoint the target document among thousands of candidates and (ii) organically connect multimodal evidence, such as tables and figures, within a limited token budget. To address these challenges, we propose HiKEY, a hierarchical tree-based multimodal retrieval framework that elevates document hierarchy to a first-class retrieval signal. Instead of simple chunking, HiKEY reconstructs a logical heterogeneous graph via Document Hierarchical Parsing (DHP), explicitly encoding parent-child relationships. Adopting a hierarchical coarse-to-fine strategy, the framework (1) performs global routing to rapidly prune the search space using hierarchical indexing, and (2) conducts fine-grained retrieval to rank sections by employing a multimodal fusion strategy that captures the most discriminative evidence. Finally, HiKEY assembles a token-efficient evidence subgraph via a hybrid structural-semantic packing strategy. Experiments on ODQA benchmarks demonstrate that HiKEY significantly outperforms page- and chunk-based baselines, improving retrieval recall by up to 12.9% and end-to-end QA performance by up to 6.8%. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Document Question Answering on FRAMES](): Document Question Answering; FRAMES; EM: 10.5. - [Document Question Answering on M3DocVQA and FRAMES (Average)](): Document Question Answering; M3DocVQA and FRAMES (Average); EM: 19. - [Document-level retrieval on M3DocVQA (test)](): Document-level retrieval; M3DocVQA (test); Recall: 84.9. - [Document-level retrieval on FRAMES (test)](): Document-level retrieval; FRAMES (test); Recall: 73.3. - [Document Question Answering on M3DocVQA](): Document Question Answering; M3DocVQA; Exact Match: 27.5. ## Original sources and implementation [Original paper]() [PDF]()