FoodTaxo: Generating Food Taxonomies with Large Language Models

TL;DR

This paper explores using large language models to automatically generate and complete food-related taxonomies, demonstrating potential but highlighting challenges in accurately positioning internal nodes.

Contribution

It introduces a method for food taxonomy generation with LLMs, including seed-based and seed-free approaches, and evaluates their effectiveness.

Findings

LLama-3 can generate food taxonomies from concepts

Seed-based methods improve taxonomy completeness

Inner node placement remains challenging

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.