Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Spatial Reasoning Questions
This work proposes Spatial Retrieval-Augmented Generation (Spatial-RAG), a framework that extends RAG to spatial tasks by integrating sparse spatial retrieval and dense semantic retrieval in Large Language Models.
Abstract
Spatial reasoning remains challenging for Large Language Models (LLMs), which struggle with spatial data retrieval and reasoning. We propose Spatial Retrieval-Augmented Generation (Spatial-RAG), a framework that extends RAG to spatial tasks by integrating sparse spatial retrieval (spatial databases) and dense semantic retrieval (LLM-based similarity). A multi-objective ranking strategy balances spatial constraints and semantic relevance, while an LLM-guided generator ensures coherent responses. Experiments on a real-world tourism dataset show that Spatial-RAG significantly improves spatial question answering, bridging the gap between LLMs and spatial intelligence.