Chatmap : Large Language Model Interaction with Cartographic Data

TL;DR

This paper demonstrates how fine-tuning a small language model with curated geospatial data enables natural language queries about urban regions using OpenStreetMap data, opening new avenues for geospatial AI applications.

Contribution

It introduces a method for fine-tuning a 1B-parameter LLM with artificial OSM data to create a linguistic interface for geospatial information, providing initial guidelines for such AI adaptations.

Findings

Successful fine-tuning of a small LLM with curated geospatial data.

The model can answer diverse questions about urban regions.

Embeddings of geospatial prompts show potential for urban retrieval applications.

Abstract

The swift advancement and widespread availability of foundational Large Language Models (LLMs), complemented by robust fine-tuning methodologies, have catalyzed their adaptation for innovative and industrious applications. Enabling LLMs to recognize and interpret geospatial data, while offering a linguistic access to vast cartographic datasets, is of significant importance. OpenStreetMap (OSM) is the most ambitious open-source global initiative offering detailed urban and rural geographic data, curated by a community of over 10 million contributors, which constitutes a great potential for LLM applications. In this study, we demonstrate the proof of concept and details of the process of fine-tuning a relatively small scale (1B parameters) LLM with a relatively small artificial dataset curated by a more capable teacher model, in order to provide a linguistic interface to the OSM data of an arbitrary urban region. Through this interface, users can inquire about a location's attributes, covering a wide spectrum of concepts, such as its touristic appeal or the potential profitability of various businesses in that vicinity. The study aims to provide an initial guideline for such generative artificial intelligence (AI) adaptations and demonstrate early signs of useful emerging abilities in this context even in minimal computational settings. The embeddings of artificially curated prompts including OSM data are also investigated in detail, which might be instrumental for potential geospatially aware urban Retrieval Augmented Generation (RAG) applications.