FoodTaxo: Generating Food Taxonomies with Large Language Models

2025/05/26 by Pascal Wullschleger, Wullschleger, Pascal, Majid Zarharan +7
Agricultural and Biological Sciences · Biochemistry, Genetics and Molecular Biology · #Culinary Culture and Tourism #Biomedical Text Mining and Ontologies #Nutrition, Genetics, and Disease

paper · pdf · doi:10.48550/arxiv.2505.19838

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.

Citations

• DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• In-Context Learning for Text Classification with Many Labels
• Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction
• Prompting Large Language Model for Machine Translation: A Case Study
• Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
• HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning
• Taxonomy Completion via Triplet Matching Network
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion
• Enriching Word Vectors with Subword Information

Related

• CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts
• FoodSEM: Large Language Model Specialized in Food Named-Entity Linking
• FoodGPT: A Large Language Model in Food Testing Domain with Incremental Pre-training and Knowledge Graph Prompt
• Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction
• FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models