Abstract: In-context learning methods for multi-turn text-to-SQL tasks often suffer from instability due to error propagation, and their performance falls short of ...
This week, we are excited to kick off SQLCon 2026 alongside FabCon in Atlanta. Bringing these SQL and Fabric communities together creates a unique opportunity to learn, connect, and share what’s next ...
Abstract: To leverage the advantages of LLM in addressing challenges in the Text-to-SQL task, we present XiYan-SQL, an innovative framework effectively generating and utilizing multiple SQL candidates ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results