Blar-SQL: Faster, Stronger, Smaller NL2SQL
This work addresses the need for efficient and cost-effective NL2SQL systems for database users, though it is incremental as it builds on existing models and methods.
The paper tackles the problem of improving natural language to SQL (NL2SQL) tasks by using task decomposition and fine-tuning open-source models like Llama-2 and Code Llama, resulting in performance comparable to GPT-4 while being 135 times smaller, 90 times faster, and over 100 times cheaper.
Large Language Models (LLMs) have gained considerable notoriety in the field of natural language to SQL tasks (NL2SQL). In this study, we show how task decomposition can greatly benefit LLMs in database understanding and query generation in order to answer human questions with an SQL query. We fined-tuned open source models, specifically Llama-2 and Code Llama, by combining 2 different models each designated to focus on one of two tasks in order to leverage each model's core competency to further increase the accuracy of the final SQL query. We propose a new framework to divide the schema into chunks in order to fit more information into a limited context. Our results are comparable with those obtained by GPT-4 at the same time being 135 times smaller, 90 times faster and more than 100 times cheaper than GPT-4.