BIRD

The BIRD dataset/benchmark contains a collection of queries used to evaluate execution-accuracy protocols for natural language to SQL translation and multi-step reasoning in enterprise AI systems.

Papers using BIRD (3)

BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL2026RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolution2026