RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles
This addresses geocoding for news articles, which is useful for tasks such as epidemic intelligence or disaster management, but it appears incremental as it applies an existing RAG method to a specific domain.
The paper tackles the problem of automatically extracting location coordinates from news articles for applications like epidemic intelligence, introducing RACCOON, a retrieval-augmented generation approach that uses LLMs to generate coordinates, with evaluation on three datasets and two LLMs showing its utility.
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.