Coordinates from Context: Using LLMs to Ground Complex Location References
This addresses a specific challenge in geospatial analysis for applications like text processing, but it is incremental as it builds on existing LLM capabilities.
The paper tackles the problem of geocoding compositional location references in unstructured text by proposing an LLM-based strategy, showing that it improves performance and that a small fine-tuned LLM can match larger off-the-shelf models.
Geocoding is the task of linking a location reference to an actual geographic location and is essential for many downstream analyses of unstructured text. In this paper, we explore the challenging setting of geocoding compositional location references. Building on recent work demonstrating LLMs' abilities to reason over geospatial data, we evaluate LLMs' geospatial knowledge versus reasoning skills relevant to our task. Based on these insights, we propose an LLM-based strategy for geocoding compositional location references. We show that our approach improves performance for the task and that a relatively small fine-tuned LLM can achieve comparable performance with much larger off-the-shelf models.