Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions
Dazhou Yu, Riyang Bao, Ruiyu Ning, Jinghong Peng, Gengchen Mai, Liang Zhao

TL;DR
Spatial-RAG is a novel framework that combines spatial databases and large language models to improve geospatial question answering by reasoning over geographic relationships and user intent.
Contribution
It introduces a hybrid spatial retriever and multi-objective optimization approach to enhance LLM-based geospatial reasoning and question answering capabilities.
Findings
Significantly improves accuracy over baselines
Enhances precision and ranking performance
Effective across multiple tourism and map-based datasets
Abstract
Answering real-world geospatial questions--such as finding restaurants along a travel route or amenities near a landmark--requires reasoning over both geographic relationships and semantic user intent. However, existing large language models (LLMs) lack spatial computing capabilities and access to up-to-date, ubiquitous real-world geospatial data, while traditional geospatial systems fall short in interpreting natural language. To bridge this gap, we introduce Spatial-RAG, a Retrieval-Augmented Generation (RAG) framework designed for geospatial question answering. Spatial-RAG integrates structured spatial databases with LLMs via a hybrid spatial retriever that combines sparse spatial filtering and dense semantic matching. It formulates the answering process as a multi-objective optimization over spatial and semantic relevance, identifying Pareto-optimal candidates and dynamically…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsConstraint Satisfaction and Optimization · Geographic Information Systems Studies · Data Management and Algorithms
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Emirates Airlines Office in Dubai · Weight Decay · Attention Dropout · Dense Connections · Linear Layer · Layer Normalization · Byte Pair Encoding · Residual Connection · Attention Is All You Need
