Optimizing ingredient substitution using large language models to enhance phytochemical content in recipes
File(s)
Published version
OA Location
Author(s)
Rita, Luís
Southern, Joshua
Laponogov, Ivan
Higgins, Kyle
Veselkov, Kirill
Type
Journal Article
Abstract
In the emerging field of computational gastronomy, aligning culinary practices with scientifically supported nutritional goals is increasingly important. This study explores how large language models (LLMs) can be applied to optimize ingredient substitutions in recipes, specifically to enhance the phytochemical content of meals. Phytochemicals are bioactive compounds found in plants, which, based on preclinical studies, may offer potential health benefits. We fine-tuned models, including OpenAI’s GPT-3.5-Turbo, DaVinci-002, and Meta’s TinyLlama-1.1B, using an ingredient substitution dataset. These models were used to predict substitutions that enhance the phytochemical content and to create a corresponding enriched recipe dataset. Our approach improved the top ingredient prediction accuracy on substitution tasks, from the baseline 34.53 ± 0.10% to 38.03 ± 0.28% on the original substitution dataset and from 40.24 ± 0.36% to 54.46 ± 0.29% on a refined version of the same dataset. These substitutions led to the creation of 1951 phytochemically enriched ingredient pairings and 1639 unique recipes. While this approach demonstrates potential in optimizing ingredient substitutions, caution must be taken when drawing conclusions about health benefits, as the claims are based on preclinical evidence. This research represents a step forward in using AI to promote healthier eating practices, providing potential pathways for integrating computational methods with nutritional science.
Date Issued
2024-12-01
Date Acceptance
2024-11-18
Citation
Machine Learning and Knowledge Extraction, 2024, 6 (4), pp.2738-2752
ISSN
2504-4990
Publisher
MDPI AG
Start Page
2738
End Page
2752
Journal / Book Title
Machine Learning and Knowledge Extraction
Volume
6
Issue
4
Copyright Statement
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
License URL
Identifier
10.3390/make6040131
Subjects
Rita, L.
Southern, J.
Laponogov, I.
Higgins, K.
Veselkov, K. Optimizing Ingredient Substitution Using Large Language Models to ingredient substitution
nutritional optimization
large language models
Publication Status
Published
Date Publish Online
2024-11-26