FoodTaxo: Generating Food Taxonomies with Large Language Models

ACL Industry Track 2025

Pascal Wullschleger^1,2Majid Zarharan²Donnacha Daly¹Marc Pouly¹Jennifer Foster²

¹Lucerne University of Applied Sciences and Arts²Dublin City University

Abstract

We investigate the utility of Large Language Models for automated taxonomy generation and completion specifically applied to tax- onomies from the food technology industry. We explore the extent to which taxonomies can be completed from a seed taxonomy or generated without a seed from a set of known concepts, in an iterative fashion using recent prompting techniques. Experiments on five taxonomies using an open-source LLM (Llama-3), while promising, point to the difficulty of correctly placing inner nodes.

Citation

@inproceedings{wullschleger-etal-2025-foodtaxo,
    title = "{F}ood{T}axo: Generating Food Taxonomies with Large Language Models",
    author = "Wullschleger, Pascal  and
      Zarharan, Majid  and
      Daly, Donnacha  and
      Pouly, Marc  and
      Foster, Jennifer",
    editor = "Rehm, Georg  and
      Li, Yunyao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.acl-industry.55/",
    pages = "784--803",
    ISBN = "979-8-89176-288-6",
    abstract = "We investigate the utility of Large Language Models for automated taxonomy generation and completion specifically applied to taxonomies from the food technology industry. We explore the extent to which taxonomies can be completed from a seed taxonomy or generated without a seed from a set of known concepts, in an iterative fashion using recent prompting techniques.Experiments on five taxonomies using an open-source LLM (Llama-3), while promising, point to the difficulty of correctly placing inner nodes."
}