Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models

arXiv (Cornell University)

Abstract

This study explores the effectiveness of Large Language Models in meal planning, focusing on their ability to identify and decompose compound ingredients. We evaluated three models-GPT-4o, Llama-3 (70b), and Mixtral (8x7b)-to assess their proficiency in recognizing and breaking down complex ingredient combinations. Preliminary results indicate that while Llama-3 (70b) and GPT-4o excels in accurate decomposition, all models encounter difficulties with identifying essential elements like seasonings and oils. Despite strong overall performance, variations in accuracy and completeness were observed across models. These findings underscore LLMs' potential to enhance personalized nutrition but highlight the need for further refinement in ingredient decomposition. Future research should address these limitations to improve nutritional recommendations and health outcomes.

Authors 5

1. Leon Kopitar

   University of Maribor

   Affiliation as printed

   Faculty of Electrical Engineering and Computer Science , University of Maribor , Slovenia

   Faculty of Health Sciences , University of Maribor , Slovenia

2. Leon Bedrač Aachen

   Leiden University

   Affiliation as printed

   The Nu B.V. , Leiden , Netherlands

3. Larissa J Strath

   Health Outcomes Solutions (United States) · Florida College

   Affiliation as printed

   Department of Health Outcomes and Biomedical Informatics , College of Medicine , University of Florida , Florida , USA

   Pain Research & Intervention Center of Excellence (PRICE) , University of Florida , Florida , USA

4. Jiang Bian

   Health Outcomes Solutions (United States) · Florida College

   Affiliation as printed

   Department of Health Outcomes and Biomedical Informatics , College of Medicine , University of Florida , Florida , USA

5. Gregor Štiglic