发表机构
East China Normal University（华东师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对临床实践指南PDF中证据锁定于视觉结构的问题，提出结构感知检索方法，将页面解析为类型化元素并按布局检索，在26份指南上显著提升元素级排序并保持页面级召回。
AI 中文摘要
指南文件以非结构化PDF形式发布，其证据被锁定在视觉结构中——表格、流程图和分级推荐——而标准检索流程将这些结构扁平化为固定大小的文本块。我们将证据访问视为一个文档图像分析问题：将每个页面图像解析为类型化结构元素，然后检索遵循文档自身布局（章节、表格行、流程图路径、分级推荐）的结构感知证据单元，每个单元保留其结构上下文，使结果指向特定元素而非整个页面。在来自9个来源的26份临床实践指南（共3,619页，中英文）及199个证据查询上，结构感知单元在BM25、稠密检索和混合检索下均将黄金元素排至首位（混合检索的元素命中率@1为0.382），相比逐元素OCR文本在元素级排序上显著提升（MRR_e +0.107，p=0.002；命中率@5的提升方向性，p=0.17），同时以3.8倍更少的上下文匹配页面级召回率（页面命中率@5为0.879对0.889，p=0.75），并明显优于ColPali视觉RAG基线（PH@5为0.497）。
英文摘要
Guideline documents are published as unstructured PDFs whose evidence is locked in visual structures---tables, flowcharts, and graded recommendations---that standard retrieval pipelines flatten into fixed-size text chunks. We cast evidence access as a document image analysis problem: parse each page image into typed structural elements, then retrieve structure-aware evidence units that follow the document's own layout (sections, table rows, flowchart paths, graded recommendations), each keeping its structural context so a result points to a specific element rather than a page. On 26 clinical practice guidelines from 9 sources (3,619 pages, Chinese and English) with 199 evidence queries, structure-aware units rank the gold element first under BM25, dense, and hybrid retrieval (hybrid Element Hit@1 of 0.382), with a significant element-level ranking gain over per-element OCR text (MRR_e +0.107, p=0.002; the Hit@5 gain is directional, p=0.17), while matching page-level recall (Page Hit@5 0.879 vs. 0.889, p=0.75) at 3.8x less context and clearly outperforming a ColPali visual-RAG baseline (PH@5 0.497).
Comments5 pages, 2 figures, 5 tables. Submitted to ICASSP 2027
