对比四种文档切分策略，发现结构感知切分最有效且成本低。
Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents
- 采用结构感知切分法，保留文档逻辑层级
- 该方法在顶K召回率上最优，计算开销更低
- 纯文本RAG对图示类文档效果差，需融合多模态
检索增强生成（RAG）已成为应对大语言模型局限性的框架，但其效果关键取决于文档切分策略——这一常被忽视的决定因素。本文通过实证研究，量化比较了四种切分方法：固定大小滑动窗口、递归式、基于语义断点和结构感知切分。实验基于油气企业专有文档语料库，涵盖文本密集型手册、表格密集型规范以及管路与仪表图（P and IDs）。结果表明，结构感知切分在整体检索有效性上表现最佳，尤其在顶K指标上优势明显，且计算成本显著低于语义或基线策略。然而，所有方法在处理P and IDs时均表现有限，凸显纯文本RAG在视觉与空间编码文档中的根本性局限。结论指出，专业领域需显式保留文档结构，未来工作应整合多模态模型以突破现有瓶颈。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has emerged as a framework to address the constraints of Large Language Models (LLMs). Yet, its effectiveness fundamentally hinges on document chunking - an often-overlooked determinant of its quality. This paper presents an empirical study quantifying performance differences across four chunking strategies: fixed-size sliding window, recursive, breakpoint-based semantic, and structure-aware. We evaluated these methods using a proprietary corpus of oil and gas enterprise documents, including text-heavy manuals, table-heavy specifications, and piping and instrumentation diagrams (P and IDs). Our findings show that structure-aware chunking yields higher overall retrieval effectiveness, particularly in top-K metrics, and incurs significantly lower computational costs than semantic or baseline strategies. Crucially, all four methods demonstrated limited effectiveness on P and IDs, underscoring a core limitation of purely text-based RAG within visually and spatially encoded documents. We conclude that while explicit structure preservation is essential for specialised domains, future work must integrate multimodal models to overcome current limitations.
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。