VIDRAFT has unveiled ViSQL, an engine that converts natural language questions into SQL queries. This engine then executes the generated SQL against a live database to verify the accuracy of the results before returning them. ViSQL, powered by VIDRAFT's Darwin-180B-RSI model, achieved an 83.80% execution accuracy on the BIRD Mini-Dev benchmark, surpassing the current public leaderboard's top score. AI
IMPACT This engine's execution-verified approach could set a new standard for NL2SQL systems, improving reliability in data access tools.
RANK_REASON The item details a new engine's performance on a specific benchmark, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
- BIRD Mini-Dev
- ChEMBL
- Darwin-180B-NL2SQL
- Darwin-180B-RSI
- EMBL's European Bioinformatics Institute
- VIDRAFT
- ViSQL
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →