FoodTaxo: Generating Food Taxonomies with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wullschleger, Pascal, Zarharan, Majid, Daly, Donnacha, Pouly, Marc, Foster, Jennifer
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915305485238272
author Wullschleger, Pascal
Zarharan, Majid
Daly, Donnacha
Pouly, Marc
Foster, Jennifer
author_facet Wullschleger, Pascal
Zarharan, Majid
Daly, Donnacha
Pouly, Marc
Foster, Jennifer
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19838
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FoodTaxo: Generating Food Taxonomies with Large Language Models
Wullschleger, Pascal
Zarharan, Majid
Daly, Donnacha
Pouly, Marc
Foster, Jennifer
Computation and Language
Artificial Intelligence
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.
title FoodTaxo: Generating Food Taxonomies with Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.19838