用图约束选关键证据，避免重复信息干扰长文档问答。
Constrained Dominant Sets for Multimodal Document Question Answering
- 构建查询增强的亲和图，以结构化约束选出相关且不冗余的证据。
- 在VisDoMBench上达66.99分，比无检索基线提升37.1分。
- 无需训练，适合长篇多模态文档的精准问答场景。
长篇多模态文档问答的瓶颈在于读者能接触到的证据，而非检索量。在长文档中，结论常在图表、图注和导语中重复出现，导致基于相似性的检索器将资源分配给近似重复内容，忽略互补证据。本文提出一种基于约束主导集（CDS）的检索器，在查询增强的亲和图上选择证据，具备三项优势：第一，将查询编码为硬性结构约束，确保每项选中内容均通过聚类锚点与问题直接关联；第二，通过谱界自动平衡相关性与冗余性，无需人工调参；第三，利用复制者动力学实现全局均衡，避免贪婪启发式带来的偏差。该方法为纯图结构设计，无需训练。使用Qwen3-VL-32B阅读器，CDS在VisDoMBench上达到66.99分的新纪录，较无检索基线提升37.1分，在MMLongBench-Doc上提升4.8分。
原文摘要 · Abstract (English)
Long multimodal document question answering is limited by which evidence reaches the reader, rather than by the quantity retrieved. In lengthy documents, findings often recur across figures, captions, and introductory sentences, causing similarity based retrievers in modern multimodal retrieval-augmented generation (RAG) systems to allocate resources to near-duplicates while overlooking complementary evidence. This work introduces a retriever that selects evidence as a Constrained Dominant Set (CDS) on a query-augmented affinity graph, offering three advantages that similarity ranking does not. First, the query is encoded as a hard structural constraint, ensuring that every selected element is directly connected to the question through the cluster anchor. Second, the relevance-redundancy balance is determined automatically by a spectral bound, eliminating the need for manually tuned trade offs required by diversity-aware selectors. Third, the selection process achieves a global equilibrium via replicator dynamics, thereby avoiding the distortions introduced by greedy heuristics. The method is inherently graph-based and does not require training. Using a Qwen3-VL-32B reader, CDS establishes a new state of the art on VisDoMBench ($66.99$ average) and improves over the no-retrieval baseline by $37.1$ points on VisDoMBench and $4.8$ on MMLongBench-Doc.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。