Research map / Large language models / Language, safety and interpretability
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
Mohammadreza Pourreza, Davood Rafiei
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply DIN-SQL decomposition and self-correction instead of few-shot prompting | GPT-4 · Spider dev | execution accuracy: 67.4 -> 74.2 | Improved |
| Apply DIN-SQL decomposition and self-correction instead of few-shot prompting | CodeX Davinci · Spider dev | execution accuracy: 61.5 -> 69.9 | Improved |
| Apply DIN-SQL decomposition and self-correction instead of GPT-4 alone | GPT-4 · BIRD dev | execution accuracy: 46.35 -> 50.72 | Improved |
| Add schema linking (ablation) | DIN-SQL with CodeX Davinci · Spider dev | execution accuracy: 65.9 -> 69.9 | Improved |
| Add self-correction (ablation) | DIN-SQL with CodeX Davinci · Spider dev | execution accuracy: 67.3 -> 69.9 | Improved |
| Add classification to select prompting complexity (ablation) | DIN-SQL with CodeX Davinci · Spider dev | execution accuracy: 63.1 -> 69.9 | Improved |
| Add classification to select prompting complexity (ablation) | DIN-SQL with CodeX Davinci · Spider dev | execution accuracy: 68.2 -> 69.9 | Improved |
| Use gentle rather than generic self-correction (ablation) | DIN-SQL with GPT-4 · Spider dev | execution accuracy: 70.0 -> 74.2 | Improved |
| Use generic rather than gentle self-correction (ablation) | DIN-SQL with CodeX Davinci · Spider dev | execution accuracy: 68.7 -> 69.9 | Improved |
| Add gentle self-correction (ablation) | DIN-SQL with GPT-4 · Spider dev | execution accuracy: 73.3 -> 74.2 | Improved |
Closest papers by meaning
- ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL (ICLR 2025 · similarity 0.90)
- CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation (AAAI 2025 · similarity 0.89)
- Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search (ICML 2025 · similarity 0.89)
- Structure-Guided Large Language Models for Text-to-SQL Generation (ICML 2025 · similarity 0.88)
- SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL (NeurIPS 2025 · similarity 0.88)
- Let's (not) just put things in Context: Test-time Training for Long-context LLMs (ICLR 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
