发表机构
NYU Abu Dhabi（纽约大学阿布扎比分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DBRAG提出一种多表检索增强生成框架，通过离线索引检索候选表、丰富摘要并重排序，结合程序辅助推理器，在Spider、GeoQuery和ATIS数据集上提升了表格检索与多表问答性能。
AI 中文摘要
近年来，大语言模型的进展为结构化数据推理引入了新能力，尤其是通过能够分析表格的程序辅助工具。然而，许多现有方法仅处理单表场景，或假设相关表格已经提供。在实践中，用户经常针对整个数据库提出复杂的数据探索查询，相关信息可能分布在多个关系中。在本工作中，我们提出了DBRAG，一种专为多表问答设计的检索增强生成框架。DBRAG首先使用离线表索引检索候选表，用查询相关的行丰富其摘要，并使用大语言模型对候选表进行重排序。然后，程序辅助推理器选择所需表格并在其完整内容上执行操作，保持初始提示上下文紧凑。在本研究使用的Spider、GeoQuery和ATIS数据集上的实验表明，DBRAG在表格检索和多表问答方面均取得了改进。
英文摘要
Recent advancements in large language models have introduced new capabilities for reasoning over structured data, particularly through program-aided tools that can analyze tables. However, many existing methods address single-table scenarios or assume that the relevant tables are already provided. In practice, users often issue complex data exploration queries over entire databases, where relevant information may be distributed across multiple relations. In this work, we introduce DBRAG, a retrieval-augmented generation framework tailored for multi-table question answering. DBRAG first retrieves candidate tables using an offline table index, enriches their summaries with query-relevant rows, and uses an LLM to rerank the candidates. A program-aided reasoner then selects the required tables and executes operations over their full contents, keeping the initial prompt context compact. Experiments on the Spider, GeoQuery, and ATIS datasets used in this study demonstrate improvements in table retrieval and multi-table question answering.
