让大模型精准理解图文混合文档，提升复杂查询推理能力。
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
- 用SQL驱动的四步流程，保持表格结构完整
- 在新基准HeteQA上超越现有方法，多跳推理准确率更高
- 适合需要跨文本与表格推理的科研和工业场景
检索增强生成（RAG）在开放域问答中表现优异，但在处理包含文本和表格的异构文档时存在明显缺陷。现有方法将表格扁平化并分块处理，破坏了表格结构，导致信息丢失，削弱大模型在多跳、全局查询中的推理能力。为此，我们提出TableRAG，一种基于SQL的统一框架，融合文本理解与复杂表格操作。TableRAG迭代执行四个步骤：上下文感知的查询分解、文本检索、SQL编程与执行、组合式中间答案生成。我们还构建了HeteQA，一个专门评估多跳异构推理能力的新基准。实验表明，TableRAG在公开数据集和HeteQA上均持续优于现有基线，建立了异构文档问答的新标杆。代码已开源：https://github.com/yxh-y/TableRAG/tree/main。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has demonstrated considerable effectiveness in open-domain question answering. However, when applied to heterogeneous documents, comprising both textual and tabular components, existing RAG approaches exhibit critical limitations. The prevailing practice of flattening tables and chunking strategies disrupts the intrinsic tabular structure, leads to information loss, and undermines the reasoning capabilities of LLMs in multi-hop, global queries. To address these challenges, we propose TableRAG, an SQL-based framework that unifies textual understanding and complex manipulations over tabular data. TableRAG iteratively operates in four steps: context-sensitive query decomposition, text retrieval, SQL programming and execution, and compositional intermediate answer generation. We also develop HeteQA, a novel benchmark designed to evaluate the multi-hop heterogeneous reasoning capabilities. Experimental results demonstrate that TableRAG consistently outperforms existing baselines on both public datasets and our HeteQA, establishing a new state-of-the-art for heterogeneous document question answering. We release TableRAG at https://github.com/yxh-y/TableRAG/tree/main.
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。