Text-to-SQL based on Large Language Models and Database Keyword Search

TL;DR

This paper introduces a novel Text-to-SQL approach that combines Large Language Models with a database keyword search platform, improving accuracy on real-world databases by enhancing schema-linking and join synthesis.

Contribution

It proposes a dynamic few-shot example strategy and leverages a keyword search platform to improve schema-linking and join synthesis in Text-to-SQL tasks for real-world databases.

Findings

Achieves higher accuracy than state-of-the-art methods on real-world database benchmarks.

Improves schema-linking precision and recall through keyword matching.

Simplifies SQL query generation by synthesizing views for complex joins.

Abstract

Text-to-SQL prompt strategies based on Large Language Models (LLMs) achieve remarkable performance on well-known benchmarks. However, when applied to real-world databases, their performance is significantly less than for these benchmarks, especially for Natural Language (NL) questions requiring complex filters and joins to be processed. This paper then proposes a strategy to compile NL questions into SQL queries that incorporates a dynamic few-shot examples strategy and leverages the services provided by a database keyword search (KwS) platform. The paper details how the precision and recall of the schema-linking process are improved with the help of the examples provided and the keyword-matching service that the KwS platform offers. Then, it shows how the KwS platform can be used to synthesize a view that captures the joins required to process an input NL question and thereby simplify the SQL query compilation step. The paper includes experiments with a real-world relational database to assess the performance of the proposed strategy. The experiments suggest that the strategy achieves an accuracy on the real-world relational database that surpasses state-of-the-art approaches. The paper concludes by discussing the results obtained.