Georeferencing complex relative locality descriptions with large language models

TL;DR

This paper demonstrates that fine-tuned Large Language Models can automatically georeference complex locality descriptions in biodiversity records with high accuracy, outperforming existing methods especially for lengthy and intricate texts.

Contribution

The study introduces a novel approach using fine-tuned LLMs with QLoRA for georeferencing complex locality descriptions, achieving significant accuracy improvements over baselines.

Findings

65% of records within 10 km radius on average across datasets

85% of records within 10 km in New York state

67% of records within 1 km in the best case

Abstract

Georeferencing text documents has typically relied on either gazetteer-based methods to assign geographic coordinates to place names, or on language modelling approaches that associate textual terms with geographic locations. However, many location descriptions specify positions relatively with spatial relationships, making geocoding based solely on place names or geo-indicative words inaccurate. This issue frequently arises in biological specimen collection records, where locations are often described through narratives rather than coordinates if they pre-date GPS. Accurate georeferencing is vital for biodiversity studies, yet the process remains labour-intensive, leading to a demand for automated georeferencing solutions. This paper explores the potential of Large Language Models (LLMs) to georeference complex locality descriptions automatically, focusing on the biodiversity collections domain. We first identified effective prompting patterns, then fine-tuned an LLM using Quantized Low-Rank Adaptation (QLoRA) on biodiversity datasets from multiple regions and languages. Our approach outperforms existing baselines with an average, across datasets, of 65% of records within a 10 km radius, for a fixed amount of training data. The best results (New York state) were 85% within 10km and 67% within 1km. The selected LLM performs well for lengthy, complex descriptions, highlighting its potential for georeferencing intricate locality descriptions.