Coordinates from Context: Using LLMs to Ground Complex Location References

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Masis, Tessa, O'Connor, Brendan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914276213522432
author Masis, Tessa
O'Connor, Brendan
author_facet Masis, Tessa
O'Connor, Brendan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08741
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Coordinates from Context: Using LLMs to Ground Complex Location References
Masis, Tessa
O'Connor, Brendan
Computation and Language
Artificial Intelligence
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.
title Coordinates from Context: Using LLMs to Ground Complex Location References
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.08741