FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Hanzhou, Yin, Kai, Chen, Zhitong, Liu, Chenyue, Mostafavi, Ali
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911514020020224
author Liu, Hanzhou
Yin, Kai
Chen, Zhitong
Liu, Chenyue
Mostafavi, Ali
author_facet Liu, Hanzhou
Yin, Kai
Chen, Zhitong
Liu, Chenyue
Mostafavi, Ali
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12084
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL
Liu, Hanzhou
Yin, Kai
Chen, Zhitong
Liu, Chenyue
Mostafavi, Ali
Information Retrieval
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.
title FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL
topic Information Retrieval
url https://arxiv.org/abs/2512.12084