DELLM + GPT-4

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Semantic Parsingonspider
Execution Accuracy (Dev)· 2024-02-18
71.68
best: 87.2 (datagpt-sql-7B + InvalidSQL-Feedback)
Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM arXiv:2402.11517
Text-To-SQLonspider
Execution Accuracy (Dev)· 2024-02-18
71.68
best: 87.2 (datagpt-sql-7B + InvalidSQL-Feedback)
Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM arXiv:2402.11517