Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL

TL;DR

Dubo-SQL introduces novel retrieval-augmented generation and fine-tuning methods that significantly improve execution accuracy in text-to-SQL tasks while reducing costs and increasing speed, setting new benchmarks on the BIRD-SQL dataset.

Contribution

The paper presents two new methods, Dubo-SQL v1 and v2, that enhance text-to-SQL performance using low-cost fine-tuning, RAG, and optimized input/output formats, surpassing existing models.

Findings

Dubo-SQL v1 sets a new record on BIRD-SQL EX.

Dubo-SQL v1 outperforms models using more expensive GPT-4.

Dubo-SQL v2 achieves higher performance with GPT-4 Turbo and RAG.

Abstract

The current state-of-the-art (SOTA) for automated text-to-SQL still falls well short of expert human performance as measured by execution accuracy (EX) on the BIRD-SQL benchmark. The most accurate methods are also slow and expensive. To advance the SOTA for text-to-SQL while reducing cost and improving speed, we explore the combination of low-cost fine tuning, novel methods for diverse retrieval-augmented generation (RAG) and new input and output formats that help large language models (LLMs) achieve higher EX. We introduce two new methods, Dubo-SQL v1 and v2. Dubo-SQL v1 sets a new record for EX on the holdout test set of BIRD-SQL. Dubo-SQL v2 achieves even higher performance on the BIRD-SQL dev set. Dubo-SQL v1 relies on LLMs from OpenAI, but uses the low-cost GPT-3.5 Turbo while exceeding the performance of the next-best model using OpenAI, which instead uses the more expensive GPT-4. Dubo-SQL v1 exceeds the performance of the next-best model using GPT-3.5 by over 20%. Dubo-SQL v2 uses GPT-4 Turbo and RAG in place of fine tuning to push EX higher.