MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation
Satya Krishna Gorti, Ilan Gofman, Zhaoyan Liu, Jiapeng Wu, Noël Vouitsis, Guangwei Yu, Jesse C. Cresswell, Rasa Hosseinzadeh
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/layer6ai-labs/msc-sqlOfficialIn paperpytorch★ 19
Abstract
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 github.com/layer6ai-labs/msc-sql.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) | MSc-SQL | Execution Accuracy % (Dev) | 65.6 | — | Unverified |
| spider | MSc-SQL | Execution Accuracy (Test) | 84.7 | — | Unverified |