MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
Joongmin Shin, Chanjun Park, Jeongbae Park, Jaehyung Seo, Heuiseok Lim
Recommendation Score
Research context
Topics
RAG, Multimodal Understanding, LLM Reasoning
Paper type
Benchmark
Best for
Useful for both
arXiv categories
Why It Matters
MultiDocFusion integrates vision and text to preserve structural context in long industrial documents, dramatically improving RAG accuracy—essential for enterprises relying on precise QA from complex PDFs, manuals, and reports.
Abstract
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.