针对表格数据设计结构感知分块方法，提升RAG检索效果。
Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation
- 以行为单位构建层级行树，按结构边界分块并去重合并。
- 相比基线减少40%~56%分块数，提升令牌利用率与处理效率。
- 适合企业表格数据检索场景，尤其需保留行列语义的RAG应用。
表格文档如CSV和Excel文件广泛用于企业数据流程，但现有检索增强生成（RAG）的分块策略主要面向非结构化文本，未考虑表格结构。本文提出结构感知表格分块（STC）框架，基于行级单元构建层次化行树表示，每行编码为键值块。STC采用基于令牌限制的结构边界对齐分块，并通过无重叠贪心合并生成密集、非重叠分块，既保留行内字段语义关系，又提升令牌利用率并减少碎片化。在MAUD数据集上的评估显示，与标准递归和基于键值的基线相比，STC分别将分块数量减少40%和56%，同时提升令牌利用率与处理效率。在检索基准测试中，混合设置下中位排名倒数（MRR）从0.3576提升至0.5945，仅用BM25检索时召回率@1从0.366升至0.754。结果表明，分块过程中保持结构信息可显著提升检索性能，凸显结构感知分块对表格数据RAG的重要性。
原文摘要 · Abstract (English)
Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented generation (RAG) are primarily designed for unstructured text and do not account for tabular structure. We propose a structure-aware tabular chunking (STC) framework that operates on row-level units by constructing a hierarchical Row Tree representation, where each row is encoded as a key-value block. STC performs token-constrained splitting aligned with structural boundaries and applies overlap-free greedy merging to produce dense, non-overlapping chunks. This design preserves semantic relationships between fields within a row while improving token utilization and reducing fragmentation. Across evaluations on the MAUD dataset, STC reduces chunk count by up to 40% and 56% compared to standard recursive and key-value based baselines, respectively, while improving token utilization and processing efficiency. In retrieval benchmarks, STC improves MRR from 0.3576 to 0.5945 in a hybrid setting and increases Recall@1 from 0.366 to 0.754 in BM25-only retrieval. These results demonstrate that preserving structure during chunking improves retrieval performance, highlighting the importance of structure-aware chunking for RAG over tabular data.
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。