FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL
This provides a practical testbed for advancing Text-to-SQL research in high-stakes disaster management domains, though it is incremental as it adapts existing methods to a new domain.
The authors tackled the lack of domain-specific, geospatially complex benchmarks in Text-to-SQL by introducing FloodSQL-Bench, a benchmark for flood management that integrates heterogeneous datasets and evaluates large language models across difficulty tiers, achieving measured performance results.
Existing Text-to-SQL benchmarks primarily focus on single-table queries or limited joins in general-purpose domains, and thus fail to reflect the complexity of domain-specific, multi-table and geospatial reasoning, To address this limitation, we introduce FLOODSQL-BENCH, a geospatially grounded benchmark for the flood management domain that integrates heterogeneous datasets through key-based, spatial, and hybrid joins. The benchmark captures realistic flood-related information needs by combining social, infrastructural, and hazard data layers. We systematically evaluate recent large language models with the same retrieval-augmented generation settings and measure their performance across difficulty tiers. By providing a unified, open benchmark grounded in real-world disaster management data, FLOODSQL-BENCH establishes a practical testbed for advancing Text-to-SQL research in high-stakes application domains.