arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2507.23104cs.CLcs.AIcs.LG

RASL: 面向海量数据库Text-to-SQL的检索增强模式链接

RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL

Amazon(亚马逊)

Jeffrey Eben, Aitzaz Ahmad, Stephen Lau

AI总结:

针对大语言模型数据库自然语言接口难以扩展到企业级海量数据目录的问题,提出RASL检索增强架构,拆解模式元数据为语义单元单独索引,兼顾表识别与列信息利用,在海量数据库上表现优于基线,无需领域微调即可适配企业场景。

摘要:

尽管基于大语言模型(LLM)的数据库自然语言接口已取得进展,但扩展至企业级数据目录仍是一个尚未被充分探索的挑战。此前应对该挑战的研究依赖特定领域微调——这增加了部署复杂度——且未能利用数据库元数据中包含的重要语义上下文。为解决这些局限,我们提出一种基于组件的检索架构,将数据库模式和元数据拆解为离散的语义单元,每个单元单独建索引以实现定向检索。我们的方法优先保障高效的表识别,同时利用列级信息,确保检索到的表总数保持在可管理的上下文预算范围内。实验表明,我们的方法维持了高召回率和准确率,在结构多样、元数据可用情况不一的海量数据库上,系统表现优于基线模型。我们的方案无需专门微调,即可打造适用于各类企业场景的实用Text-to-SQL系统,填补了自然语言数据库接口中关键的可扩展性缺口。

英文摘要:

Despite advances in large language model (LLM)-based natural language interfaces for databases, scaling to enterprise-level data catalogs remains an under-explored challenge. Prior works addressing this challenge rely on domain-specific fine-tuning - complicating deployment - and fail to leverage important semantic context contained within database metadata. To address these limitations, we introduce a component-based retrieval architecture that decomposes database schemas and metadata into discrete semantic units, each separately indexed for targeted retrieval. Our approach prioritizes effective table identification while leveraging column-level information, ensuring the total number of retrieved tables remains within a manageable context budget. Experiments demonstrate that our method maintains high recall and accuracy, with our system outperforming baselines over massive databases with varying structure and available metadata. Our solution enables practical text-to-SQL systems deployable across diverse enterprise settings without specialized fine-tuning, addressing a critical scalability gap in natural language database interfaces.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑