MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation
This addresses accessibility, privacy, and latency issues for non-experts interacting with databases, though it is incremental as it builds on existing text-to-SQL methods.
The paper tackles the problem of text-to-SQL generation by developing a small, efficient open-source model called MSc-SQL, which critiques multiple candidate SQL generations using metadata to achieve state-of-the-art performance among open-source models while remaining competitive with larger models at lower cost.
Text-to-SQL generation enables non-experts to interact with databases via natural language. Recent advances rely on large closed-source models like GPT-4 that present challenges in accessibility, privacy, and latency. To address these issues, we focus on developing small, efficient, and open-source text-to-SQL models. We demonstrate the benefits of sampling multiple candidate SQL generations and propose our method, MSc-SQL, to critique them using associated metadata. Our sample critiquing model evaluates multiple outputs simultaneously, achieving state-of-the-art performance compared to other open-source models while remaining competitive with larger models at a much lower cost. Full code can be found at https://github.com/layer6ai-labs/msc-sql.