SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists

TL;DR

SPOT is an innovative natural language interface that simplifies access to OpenStreetMap data for investigative journalists, enabling non-technical users to perform geospatial searches through intuitive scene descriptions.

Contribution

It introduces a novel approach combining fine-tuned LLMs with a synthetic data pipeline to provide accurate, reliable natural language querying of OSM data, specifically tailored for journalism.

Findings

Achieves reliable natural language access to OSM data

Addresses hallucinations and tagging inconsistencies in model outputs

Enables non-technical users to perform geospatial searches effectively

Abstract

OpenStreetMap (OSM) is a vital resource for investigative journalists doing geolocation verification. However, existing tools to query OSM data such as Overpass Turbo require familiarity with complex query languages, creating barriers for non-technical users. We present SPOT, an open source natural language interface that makes OSM's rich, tag-based geographic data more accessible through intuitive scene descriptions. SPOT interprets user inputs as structured representations of geospatial object configurations using fine-tuned Large Language Models (LLMs), with results being displayed in an interactive map interface. While more general geospatial search tasks are conceivable, SPOT is specifically designed for use in investigative journalism, addressing real-world challenges such as hallucinations in model output, inconsistencies in OSM tagging, and the noisy nature of user input. It combines a novel synthetic data pipeline with a semantic bundling system to enable robust, accurate query generation. To our knowledge, SPOT is the first system to achieve reliable natural language access to OSM data at this level of accuracy. By lowering the technical barrier to geolocation verification, SPOT contributes a practical tool to the broader efforts to support fact-checking and combat disinformation.