FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL
Proceedings of the AAAI Symposium Series · 23.06.2026 · 9 (1) · 83-90
DOI: 10.1609/aaaiss.v9i1.42909 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 23.06.2026. Verfasst von Hanzhou Liu und 4 weiteren Autor:innen.
Abstract (Originalsprache)
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.
Zitieren
APA
Liu, H., Yin, K., Chen, Z., Liu, C., & Mostafavi, A. (2026). FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL. Proceedings of the AAAI Symposium Series, 9(1), 83-90. https://doi.org/10.1609/aaaiss.v9i1.42909
Vancouver
Liu H, Yin K, Chen Z, Liu C, Mostafavi A. FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL. Proceedings of the AAAI Symposium Series. 2026;9(1):83-90. doi:10.1609/aaaiss.v9i1.42909
BibTeX
@article{Liu2026,
author = {Liu, Hanzhou and Yin, Kai and Chen, Zhitong and Liu, Chenyue and Mostafavi, Ali},
title = {FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {9},
number = {1},
pages = {83--90},
doi = {10.1609/aaaiss.v9i1.42909}
}
EUVIMED