# MapQA: Open-domain Geospatial Question Answering on Map Data

arXiv: https://arxiv.org/abs/2503.07871 · HTML: https://mlsanity.com/paper/2503.07871/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [C3: Zero-shot Text-to-SQL with ChatGPT](https://mlsanity.com/paper/2307.07306/) (2023)
- [SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning](https://mlsanity.com/paper/1711.04436/) (2017)
- [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2012.12627/) (2020)
- [Structure-Grounded Pretraining for Text-to-SQL](https://mlsanity.com/paper/2010.12773/) (2020)
- [GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding](https://mlsanity.com/paper/2310.14478/) (2023)
- [NeuroNER: an easy-to-use program for named-entity recognition based on neural networks](https://mlsanity.com/paper/1705.05487/) (2017)
- [Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions](https://mlsanity.com/paper/2105.09392/) (2021)
- [Towards General-Purpose Representation Learning of Polygonal Geometries](https://mlsanity.com/paper/2209.15458/) (2022)
- [Template-Based Question Answering over Linked Geospatial Data](https://mlsanity.com/paper/2007.07060/) (2020)
- [Joint Spatio-Textual Reasoning for Answering Tourism Questions](https://mlsanity.com/paper/2009.13613/) (2020)
- [Large Scale Question Answering using Tourism Data](https://mlsanity.com/paper/1909.03527/) (2019)

## Built on by (most cited first, 15 of 15)

- [Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts](https://mlsanity.com/paper/2601.16965/) (2026)
- [MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration](https://mlsanity.com/paper/2509.05933/) (2025)
- [FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models](https://mlsanity.com/paper/2512.08016/) (2025)
- [MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs](https://mlsanity.com/paper/2602.18600/) (2026)
- [From Questions to Queries: An AI-powered Multi-Agent Framework for Spatial Text-to-SQL](https://mlsanity.com/paper/2510.21045/) (2025)
- [OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents](https://mlsanity.com/paper/2607.09068/) (2026)
- [A Dataset for Spatiotemporal-Sensitive POI Question Answering](https://mlsanity.com/paper/2505.10928/) (2025)
- [m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning](https://mlsanity.com/paper/2601.19099/) (2026)
- [MapVerse: A Benchmark for Geospatial Question Answering on Diverse Real-World Maps](https://mlsanity.com/paper/2602.10518/) (2026)
- [EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration](https://mlsanity.com/paper/2604.07070/) (2026)
- [ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering](https://mlsanity.com/paper/2604.17944/) (2026)
- [ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes](https://mlsanity.com/paper/2605.27590/) (2026)
- [MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning](https://mlsanity.com/paper/2608.03882/) (2026)
- [GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks](https://mlsanity.com/paper/2608.07411/) (2026)
- [Question-Specific Knowledge Graphs for Efficient Visual Reasoning](https://mlsanity.com/paper/2609.35942/) (2026)

## Abstract (arXiv)

Geospatial question answering (QA) is a fundamental task in navigation and point of interest (POI) searches. While existing geospatial QA datasets exist, they are limited in both scale and diversity, often relying solely on textual descriptions of geo-entities without considering their geometries. A major challenge in scaling geospatial QA datasets for reasoning lies in the complexity of geospatial relationships, which require integrating spatial structures, topological dependencies, and multi-hop reasoning capabilities that most text-based QA datasets lack. To address these limitations, we introduce MapQA, a novel dataset that not only provides question-answer pairs but also includes the geometries of geo-entities referenced in the questions. MapQA is constructed using SQL query templates to extract question-answer pairs from OpenStreetMap (OSM) for two study regions: Southern California and Illinois. It consists of 3,154 QA pairs spanning nine question types that require geospatial reasoning, such as neighborhood inference and geo-entity type identification. Compared to existing datasets, MapQA expands both the number and diversity of geospatial question types. We explore two approaches to tackle this challenge: (1) a retrieval-based language model that ranks candidate geo-entities by embedding similarity, and (2) a large language model (LLM) that generates SQL queries from natural language questions and geo-entity attributes, which are then executed against an OSM database. Our findings indicate that retrieval-based methods effectively capture concepts like closeness and direction but struggle with questions that require explicit computations (e.g., distance calculations). LLMs (e.g., GPT and Gemini) excel at generating SQL queries for one-hop reasoning but face challenges with multi-hop reasoning, highlighting a key bottleneck in advancing geospatial QA systems.