Large Language Models for Spatial Analysis Queries

Summary: Survey of LLMs for spatial analysis queries with a taxonomy from use-as-is and fine-tuning to full retraining and LLM-internal modifications to capture spatial primitives and reasoning. Proposes benchmarks, evaluation protocols, and pinpoints research gaps in spatial semantics, geometric operators, and efficiency/accuracy trade-offs for LLM-driven spatial DBMS. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 14368
Venue: VLDB
Year: 2025
Pagerank: 5.093636e-05
Overall Rank: 11,061 | 24.12%
DOI: 10.14778/3750601.3750693

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Youssef Hussein (University of Minnesota)
2. Mohamed Hemdan (University of Minnesota)
3. Mohamed F. Mokbel (University of Minnesota)

BibTeX Citation

@article{hussein_vldb25,
        title = {{Large Language Models for Spatial Analysis Queries}},
        author = {Hussein, Youssef and Hemdan, Mohamed and Mokbel, Mohamed F.},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {12},
        pages = {5451--5454},
        doi = {10.14778/3750601.3750693},
        url = {https://doi.org/10.14778/3750601.3750693},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 17 of 17 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
420	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00018789852
1,793	TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data	2022	VLDB	9.7435472e-05
3,536	How Large Language Models Will Disrupt Data Management	2023	VLDB	7.3297343e-05
4,449	From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management	2022	VLDB	6.697553e-05
4,515	ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models	2024	VLDB	6.6492389e-05
4,836	Transformers for Tabular Data Representation: A Tutorial on Models and Applications	2022	VLDB	6.4848269e-05
5,606	Analyzing How BERT Performs Entity Matching	2022	VLDB	6.1521568e-05
7,379	Comparing Synopsis Techniques for Approximate Spatial Data Analysis	2019	VLDB	5.629255e-05
7,505	Kamel: A Scalable BERT-based System for Trajectory Imputation	2024	VLDB	5.6029996e-05
7,871	TSGAssist: An Interactive Assistant Harnessing LLMs and RAG for Time Series Generation Recommendations and Benchmarking	2024	VLDB	5.5271792e-05
8,435	Spatial Data Quality in the IoT Era: Management and Exploitation	2022	SIGMOD	5.4253644e-05
8,903	DataLoom: Simplifying Data Loading with LLMs	2024	VLDB	5.3486551e-05
9,626	Spatial Query Optimization With Learning	2024	VLDB	5.2434488e-05
9,631	Lingua Manga: A Generic Large Language Model Centric System for Data Curation	2023	VLDB	5.2434488e-05
9,632	Fast Network K-function-based Spatial Analysis	2022	VLDB	5.2434488e-05
9,636	KDV-Explorer: A Near Real-Time Kernel Density Visualization System for Spatial Analysis	2021	VLDB	5.2434488e-05
11,873	Flash in Action: Scalable Spatial Data Analysis Using Markov Logic Networks	2019	VLDB	5.093636e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	3,310	Similarity Query Processing for High-Dimensional Data	2020	VLDB
2	6,101	LLM for Data Management	2024	VLDB
3	14,388	Spatial Databases	1992	VLDB
4	13,343	Database Perspective on LLM Inference Systems	2025	VLDB
5	6,382	The Era of Big Spatial Data	2017	VLDB
6	8,823	Querying Geo-Textual Data: Spatial Keyword Queries and Beyond	2016	SIGMOD
7	11,979	Query Processing Techniques for Big Spatial-Keyword Data	2017	SIGMOD
8	10,374	GeoKGM: A Multimodal Large Language Model for Zero-Shot Knowledge Graph Completion in Geospatial Databases	2026	SIGMOD
9	9,626	Spatial Query Optimization With Learning	2024	VLDB
10	8,722	Machine Learning Meets Big Spatial Data	2019	VLDB