@inproceedings{haider-etal-2025-quantification,
    title = "Quantification of Biodiversity from Historical Survey Text with {LLM}-based Best-Worst-Scaling",
    author = "Haider, Thomas  and
      Perschl, Tobias  and
      Rehbein, Malte",
    editor = "Basile, Valerio  and
      Bosco, Cristina  and
      Grasso, Francesca  and
      Ibrohim, Muhammad Okky  and
      Skeppstedt, Maria  and
      Stede, Manfred",
    booktitle = "Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025)",
    month = mar,
    year = "2025",
    address = "Tallinn, Estonia",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/landing_page/2025.nlp4ecology-1.13/",
    pages = "61--67",
    ISBN = "978-9908-53-114-4",
    abstract = "In this study, we evaluate methods to determine the frequency of species via quantity estimation from historical survey text. To that end, we formulate classification tasks and finally show that this problem can be adequately framed as a regression task using Best-Worst Scaling (BWS) with Large Language Models (LLMs). We test Ministral-8B, DeepSeek-V3, and GPT-4, finding that the latter two have reasonable agreement with humans and each other. We conclude that this approach is more cost-effective and similarly robust compared to a fine-grained multi-class approach, allowing automated quantity estimation across species."
}