PromptMind Team at EHRSQL-2024: Improving Reliability of SQL Generation using Ensemble LLMs

TL;DR

This paper introduces ensemble methods leveraging large language models to improve the reliability and accuracy of Text-to-SQL systems for electronic health records, achieving high performance in a shared task competition.

Contribution

It proposes ensemble LLM techniques for domain-specific Text-to-SQL generation, enhancing reliability and accuracy over individual models.

Findings

Achieved high execution accuracy in EHRSQL query generation.

Ensemble approach reduced errors and improved reliability.

Secured 2nd place in the shared task competition.

Abstract

This paper presents our approach to the EHRSQL-2024 shared task, which aims to develop a reliable Text-to-SQL system for electronic health records. We propose two approaches that leverage large language models (LLMs) for prompting and fine-tuning to generate EHRSQL queries. In both techniques, we concentrate on bridging the gap between the real-world knowledge on which LLMs are trained and the domain specific knowledge required for the task. The paper provides the results of each approach individually, demonstrating that they achieve high execution accuracy. Additionally, we show that an ensemble approach further enhances generation reliability by reducing errors. This approach secured us 2nd place in the shared task competition. The methodologies outlined in this paper are designed to be transferable to domain-specific Text-to-SQL problems that emphasize both accuracy and reliability.