DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models
This addresses data privacy concerns by enabling competitive performance with small open-source models, though it is incremental as it builds on existing fine-tuning methods.
The paper tackles the reliance on proprietary large language models for text-to-SQL tasks by introducing a two-stage fine-tuning approach that decomposes the task, improving execution accuracy by 3 to 7 percent on cross-domain datasets.
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, effectively aligning the performance of open-source models with their proprietary counterparts.