让检索系统理解文档的结构布局，提升混合文本表格查询效果
Topo-RAG: Topology-aware retrieval for hybrid text-table documents
- 区分文本与表格数据，分别用不同方式处理信息结构
- 在混合查询上相比传统方法提升18.4%的nDCG@10指标
- 适合需要理解复杂企业文档结构的场景
在企业级数据集中，文档往往不是纯文本或纯表格，而是叙事内容与结构化数据的复杂混合。当前的检索增强生成（RAG）系统通常采用线性化处理：将多维表格转化为简单的Markdown格式文本字符串，期望嵌入模型能捕捉其表格几何结构。但已有研究表明这种方法在数学上是不充分的。本文提出Topo-RAG框架，挑战‘一切皆文本’的假设，设计双路径架构：流式叙述通过传统密集检索器处理，而表格结构则由单元格感知的后期交互机制保留其空间关系。在模拟真实复杂度的合成企业语料SEC-25上评估显示，对于混合查询任务，Topo-RAG相较标准线性化方法在nDCG@10上提升18.4%。这不仅是更精准的检索，更是对信息形态的深层理解。
原文摘要 · Abstract (English)
In enterprise datasets, documents are rarely pure. They are not just text, nor just numbers; they are a complex amalgam of narrative and structure. Current Retrieval-Augmented Generation (RAG) systems have attempted to address this complexity with a blunt tool: linearization. We convert rich, multidimensional tables into simple Markdown-style text strings, hoping that an embedding model will capture the geometry of a spreadsheet in a single vector. But it has already been shown that this is mathematically insufficient. This work presents Topo-RAG, a framework that challenges the assumption that "everything is text". We propose a dual architecture that respects the topology of the data: we route fluid narrative through traditional dense retrievers, while tabular structures are processed by a Cell-Aware Late Interaction mechanism, preserving their spatial relationships. Evaluated on SEC-25, a synthetic enterprise corpus that mimics real-world complexity, Topo-RAG demonstrates an 18.4% improvement in nDCG@10 on hybrid queries compared to standard linearization approaches. It's not just about searching better; it's about understanding the shape of information.
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。