DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models

Leading models for the text-to-SQL task heavily rely on proprietary Large Language Models (LLMs), posing concerns over data privacy. Closing the performance gap between small open-source models and large proprietary models is crucial to mitigate this reliance. To this end, we introduce a novel two-stage fine-tuning approach that decomposes the task into two simpler tasks. Through comprehensive evaluation on two large cross-domain datasets and two small LLMs, we show that this approach improves execution accuracy by 3 to 7 percent, …

concerns cs.cl cs.db cs.hc data data privacy fine-tuning gap language language models large language large language models llms novel open-source models performance privacy proprietary proprietary models reliance small sql stage text text-to-sql