# Utilizing large language models to construct a dataset of Württemberg’s 19th-century fauna from historical records

## TL;DR

This paper shows how AI can automatically extract information about 19th-century animal species from old texts in Württemberg, making it easier to study historical biodiversity.

## Contribution

The novel use of large language models to extract and link species mentions from historical texts to GBIF identifiers is introduced.

## Key findings

- LLMs achieved high recall (92.6%) and precision (95.3%) in identifying species mentions in historical texts.
- Species identifiers were matched to GBIF with 83.0% accuracy.
- The approach is scalable and adaptable to other historical contexts and languages.

## Abstract

Constructing datasets on past biodiversity from historical sources is crucial for understanding long-term ecological changes. Typically, compiling such datasets relies on prior knowledge of the sources’ composition and requires considerable manual effort. To overcome these challenges, we implement an automated approach based on prompted large language models (LLMs) to detect mentions of species in texts from 19th-century Württemberg and link these mentions to identifiers in the GBIF database. Based on our evaluation, we find that LLMs can reliably identify species in the texts with high recall (92.6%) and precision (95.3%), while providing estimates of the correct species identifier with considerable accuracy (83.0%). As our approach is easily scalable and adaptable to other contexts and languages, it offers a promising way to advance dataset generation from historical material using limited resources.