RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles

TL;DR

RACCOON is a novel retrieval-augmented generation method that automatically extracts precise location coordinates from news articles using large language models, enhancing geocoding accuracy for applications like disaster response.

Contribution

It introduces the first RAG-based geocoding approach leveraging pre-trained LLMs, combining retrieval of candidate locations with generation of coordinates from news text.

Findings

RACCOON outperforms baseline methods across datasets.

The approach effectively integrates retrieval and generation for accurate geocoding.

Evaluation shows RACCOON's utility and robustness in different scenarios.

Abstract

Geocoding involves automatic extraction of location coordinates of incidents reported in news articles, and can be used for epidemic intelligence or disaster management. This paper introduces Retrieval-Augmented Coordinate Capture Of Online News articles (RACCOON), an open-source geocoding approach that extracts geolocations from news articles. RACCOON uses a retrieval-augmented generation (RAG) approach where candidate locations and associated information are retrieved in the form of context from a location database, and a prompt containing the retrieved context, location mentions and news articles is fed to an LLM to generate the location coordinates. Our evaluation on three datasets, two underlying LLMs, three baselines and several ablation tests based on the components of RACCOON demonstrate the utility of RACCOON. To the best of our knowledge, RACCOON is the first RAG-based approach for geocoding using pre-trained LLMs.