Technical Report - A Comparative Evaluation of Schema Subsetting for LLM-based NL-to-SQL over Large-Schema Databases
This paper systematically evaluates 7 real-world schema subsetting modules across 3 contemporary NL-to-SQL benchmarks, and introduces BigBird–an expansion of the Bird benchmark datasets that provides additional data for evaluating subsetting of large schemas, and introduces new subsetting-specific performance and effic...