End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation

TL;DR

This paper introduces an end-to-end framework that uses large language models and prompt engineering to identify the correct database before generating SQL queries, improving accuracy in multi-database scenarios.

Contribution

It presents a novel three-stage approach combining LLMs, a database prediction model, and error correction to enhance text-to-SQL performance in complex database environments.

Findings

Outperforms state-of-the-art in database intent prediction

Achieves higher SQL generation accuracy

Effective in multi-database query scenarios

Abstract

Text-to-SQL bridges the gap between natural language and structured database language, thus allowing non-technical users to easily query databases. Traditional approaches model text-to-SQL as a direct translation task, where a given Natural Language Query (NLQ) is mapped to an SQL command. Recent advances in large language models (LLMs) have significantly improved translation accuracy, however, these methods all require that the target database is pre-specified. This becomes problematic in scenarios with multiple extensive databases, where identifying the correct database becomes a crucial yet overlooked step. In this paper, we propose a three-stage end-to-end text-to-SQL framework to identify the user's intended database before generating SQL queries. Our approach leverages LLMs and prompt engineering to extract implicit information from natural language queries (NLQs) in the form of a ruleset. We then train a large db\_id prediction model, which includes a RoBERTa-based finetuned encoder, to predict the correct Database identifier (db\_id) based on both the NLQ and the LLM-generated rules. Finally, we refine the generated SQL by using critic agents to correct errors. Experimental results demonstrate that our framework outperforms the current state-of-the-art models in both database intent prediction and SQL generation accuracy.