Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison

TL;DR

This paper systematically compares six open-source large language models on Text-to-SQL tasks across multiple benchmarks, revealing a significant performance gap compared to closed-source models like GPT-3.5.

Contribution

It provides a comprehensive evaluation of open-source LLMs for Text-to-SQL, highlighting their current limitations relative to proprietary models.

Findings

Open-source models underperform GPT-3.5 in Text-to-SQL tasks.

Performance varies across different prompting strategies.

Significant gap remains between open-source and closed-source models.

Abstract

The success of ChatGPT has ignited an AI race, with researchers striving to develop new large language models (LLMs) that can match or surpass the language understanding and generation abilities of commercial ones. In recent times, a number of models have emerged, claiming performance near that of GPT-3.5 or GPT-4 through various instruction-tuning methods. As practitioners of Text-to-SQL parsing, we are grateful for their valuable contributions to open-source research. However, it is important to approach these claims with a sense of scrutiny and ascertain the actual effectiveness of these models. Therefore, we pit six popular large language models against each other, systematically evaluating their Text-to-SQL parsing capability on nine benchmark datasets with five different prompting strategies, covering both zero-shot and few-shot scenarios. Regrettably, the open-sourced models fell significantly short of the performance achieved by closed-source models like GPT-3.5, highlighting the need for further work to bridge the performance gap between these models.