研究人员开发了一种新的检索方法，称为约束主导集（CDS），用于多模态文档问答。该技术解决了当前系统中难以处理长文档的局限性，通过选择互补证据而非近乎重复的证据。CDS将查询编码为结构约束，自动平衡相关性和冗余性，并通过实现全局均衡来避免贪婪启发式方法。当与Qwen3-VL-32B阅读器一起使用时，CDS在VisDoMBench上设定了新的最先进水平，并显著提高了MMLongBench-Doc的性能。 AI
影响 在多模态问答基准测试中确立了新的SOTA，改进了长文档的检索。
排序理由 该集群包含一篇研究论文，详细介绍了一种新的多模态文档问答方法，包括基准测试结果。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
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 multi…
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 multi…