针对工业文档结构复杂问题，提出多模态分块方法提升RAG问答准确率。
MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
- 融合视觉解析与OCR，识别文档区域并提取文本
- 用大模型重构文档层级结构，分块精度提升8-15%
- 适合处理长篇工业文档的RAG系统开发者使用
基于RAG的问答已成处理长篇工业文档的有效方法。但传统文本分块方式常忽略复杂文档结构，导致信息丢失与回答质量下降。为此，我们提出MultiDocFusion，一种多模态分块流水线：(i) 基于视觉的文档区域检测，(ii) 通过OCR提取区域文本，(iii) 利用大语言模型进行文档章节层级解析（DSHP-LLM）重建文档结构为层次树，(iv) 采用深度优先搜索（DFS）分组构建层次化分块。在多个工业基准上的实验证明，相比基线方法，MultiDocFusion将检索精确率提升8-15%，ANLS问答得分提升2-3%，凸显显式利用文档层级对多模态文档问答的关键作用。这些显著性能提升强调了结构感知分块在增强RAG问答系统保真度中的必要性。
原文摘要 · Abstract (English)
RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial document structures, causing information loss and reduced answer quality. To address this, we introduce MultiDocFusion, a multimodal chunking pipeline that integrates: (i) detection of document regions using vision-based document parsing, (ii) text extraction from these regions via OCR, (iii) reconstruction of document structure into a hierarchical tree using large language model (LLM)-based document section hierarchical parsing (DSHP-LLM), and (iv) construction of hierarchical chunks through DFS-based grouping. Extensive experiments across industrial benchmarks demonstrate that MultiDocFusion improves retrieval precision by 8-15% and ANLS QA scores by 2-3% compared to baselines, emphasizing the critical role of explicitly leveraging document hierarchy for multimodal document-based QA. These significant performance gains underscore the necessity of structure-aware chunking in enhancing the fidelity of RAG-based QA systems.
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。