HyperDoc is proposed, a document RAG framework that constructs compact yet sufficient evidence while preserving document relations and constructs a document hypergraph to explicitly capture structural, logical, and cross-modal relationships among multimodal document elements.
Abstract
Long-context multimodal document question answering (QA) has become an important yet challenging task for modern vision-language models (VLMs), as it requires reasoning over evidence dispersed across pages and modalities within limited input budgets. Current pipelines adopt retrieval-augmented generation (RAG) to select multimodal evidence for downstream VLMs. However, existing systems mainly rely on static selection rules over fixed-granularity retrieval units such as pages or blocks, resulting in information loss during retrieval and suboptimal performance in downstream reasoning. To alleviate these issues, we formulate the core task as budget-aware evidence selection over structured document evidence and propose HyperDoc, a document RAG framework that constructs compact yet sufficient evidence while preserving document relations. Specifically, HyperDoc constructs a document hypergraph to explicitly capture structural, logical, and cross-modal relationships among multimodal document elements. Over this structured evidence space, HyperDoc performs adaptive cost-aware hyperedge selection based on query intent and input budget. Extensive experiments on three representative benchmarks demonstrate that HyperDoc outperforms various types of state-of-the-art baselines.
Long-document visual question answering requires models to locate sparse question-relevant evidence across many pages and understand fine-grained textual and visual content. Processing an entire document at high resolution is computationally expensive, whereas reduced visual fidelity and irrelevant pages can impair bot...
Hong Nie, Jun Yu, Bo Wang et al.· Proceedings of the 34th ACM...· 0 citations
This review traces the evolution of CQA from retrieval and ranking through neural semantic matching and pretrained Transformer models to retrieval-augmented generation and large language models, with particular emphasis on multi-label question understanding and multi-document evidence integration.
Yan Tan· Computers and artificial int...· 0 citations
Complex Web question answering requires retrieval-augmented generation (RAG) systems to identify target entities from multi-clue descriptions and connect evidence scattered across long Web pages. Individual pages often support only some of the required semantic constraints, while clues discovered on one page guide subs...
Lin-Yao Zheng, Xu-Hang Shi, Zhi-Fang Mao et al.· 0 citations
Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This leaves an important gap between leaderboard performance and realistic long-document retrieval, where the evidence needed to answer a query may span multiple pages or even...
Simon Ott, Yu-Fan Chen, Rui-Ping Liu et al.· 0 citations
Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and interpretation failures. We present VELD-QA, a large-scale benchmark for Visual Evidence grounding and question answering in Long Documents....
Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang et al.· 0 citations
DuQUAD is proposed, a multi-document QA framework that mitigates positional bias through dual-view reasoning and quality-aware evidence pruning, and substantially reducing computational cost compared to existing multi-agent frameworks.
Yeonjun Choi, Seyeong Jeong, Jong Wook Kim et al.· Proceedings of the 2026 Conf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.