Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients
The open-source Llama-3 (70B) model achieved the best performance, outperforming the commercial GPT-4o model, showing its superior ability to consistently break down compound ingredients into precise quantities within meal plans and illustrating its potential to enhance meal customization and nutritional analysis. These findings underscore the potential role of advanced LLMs in precision nutrition and their application in promoting healthier dietary practices tailored to individual preferences and needs.
Authors
- Larissa J. Strath (ORCID: https://orcid.org/0000-0002-9616-0177)
- Gregor Štiglic (ORCID: https://orcid.org/0000-0002-0183-8679)
- Jiang Bian (ORCID: https://orcid.org/0000-0002-2238-5429)
- Leon Kopitar (ORCID: https://orcid.org/0000-0002-6647-9988)
- Leon Bedrač
Institutions
- Leiden University (NL)
- Regenstrief Institute (US)
- University of Florida (US)
- University of Maribor (SI)
- Indiana University Bloomington (US)
- University of Edinburgh (GB)
Publication Details
- Journal
- Nutrients
- Published
- 2025-04-29
- DOI
- https://doi.org/10.3390/nu17091492
- Citations
- 5
- Primary Topic
- Nutrition, Genetics, and Disease
- Type
- article
- Field-Weighted Citation Impact
- 9.09
Funders
- European Commission
- HORIZON EUROPE Framework Programme
- Research Executive Agency