Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM

Open paper
Benchmark Model Rank Results
text-to-sql-on-birdDELLM + MAC-SQL#13Execution Accuracy % (Dev): 48.92
text-to-sql-on-spiderDELLM + GPT-4#15Execution Accuracy (Dev): 71.68

Rank counts only results with a code link.