New CA-SQL system boosts LLM Text-to-SQL accuracy on complex queries

Researchers have developed CA-SQL, a new Text-to-SQL system designed to improve the accuracy of large language models on complex database queries. CA-SQL dynamically adjusts its search for potential solutions based on the estimated difficulty of a query, employing a novel prompt seeding method and a voting mechanism to select the best candidate. This approach achieved a state-of-the-art score of 51.72% on the challenging tier of the BIRD benchmark using only GPT-4o-mini, outperforming larger models. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances LLM capabilities for complex database querying, potentially improving data analysis tools.

RANK_REASON The cluster contains an academic paper detailing a new method for Text-to-SQL tasks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CA-SQL
• GPT-4o-mini
• BIRD benchmark

• paper
• product