将分页识别结果整合为连贯文档结构，提升信息检索效果。
MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
- 分四步恢复文本、表格、标题层级与图文关联，实现跨页结构重建。
- 在五种OCR模型上标题层级准确率提升超20%，支持长文档处理。
- 轻量级设计适合实际部署，特别适合RAG等下游应用。
基于视觉语言模型（VLM）的OCR模型已成为文档解析的主流选择，能精准提取单页中的段落、表格等元素及其边界框和文本内容。然而，下游应用如检索增强生成（RAG）需要连贯的文档级信息，而现有模型常因跨页连续性断裂，无法恢复被页面边界截断的段落或表格等结构。这些关系跨越多页，需联合分析标题、段落、表格和图像。为此，我们提出MinerU-Popo——一种轻量且通用的后处理框架，可将多种解析器输出的分页结果转化为一致的文档级结构。该框架将问题分解为四个子任务：文本截断恢复、表格截断恢复、标题层级重建和图文关联。我们构建了面向任务的数据引擎，通过任务特异性输入过滤生成30K标注数据，并用其微调轻量模型Qwen3-VL-4B。为支持长文档，引入重叠同步的动态分块策略，对齐分块输出并保持全局一致性。最终将对齐结果组织为树状文档结构，进一步通过节点分块与摘要增强，便于下游检索与分析。实验表明，MinerU-Popo在所有五种测试的OCR模型上均使标题层级TEDS提升至少20%，显著提高RAG准确性并降低每查询延迟。
原文摘要 · Abstract (English)
VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together with their bounding boxes and textual content. However, downstream applications such as RAG require coherent document-level information, whereas these models often break cross-page continuity and fail to recover disrupted structures, such as paragraphs and tables truncated by page boundaries. Such relationships are not confined to a single page; instead, they require joint analysis of titles, paragraphs, tables, and images spanning multiple pages. A natural solution is therefore to reuse existing OCR outputs and reconstruct document-level logical structures through post-processing. To this end, we propose MinerU-Popo, a lightweight and universal framework for POst-Processing OCR outputs, which converts page-level results from diverse parsers into coherent document-level structures. MinerU-Popo decomposes the problem into four focused subtasks: text truncation recovery, table truncation recovery, title hierarchy reconstruction, and image-text association. To address these effectively, we build a task-oriented data engine with task-specific input filtering, and use the generated data (30K) to fine-tune a lightweight post-processing model (Qwen3-VL-4B). To support long documents, we introduce dynamic chunking with overlap-based synchronization, which aligns chunk-level outputs from the fine-tuned model and preserves global consistency. Finally, we assemble the aligned outputs into a tree-structured document representation, further enriched with node chunking and summaries for downstream retrieval and analysis. Empirical results show MinerU-Popo improves title-hierarchy TEDS by at least 20% across all five tested OCR models, improves RAG accuracy and reduces per-query latency.
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。