SectionDescription
Project TitleOptimization of Ingredient Substitutions Using Large Language Models to Enhance Phytochemical Content in Recipes
Project OverviewThis innovative research leverages advanced Natural Language Processing models such as GPT-3.5 and TinyLlama to intelligently suggest ingredient substitutions in recipes, aiming to increase the phytochemical (bioactive plant compounds) content and improve the nutritional and health properties of foods.
Objectives- Predict compatible and optimal ingredient substitutions for recipes- Enhance phytochemical and nutritional value of dishes- Develop a portfolio of novel, health-optimized recipes- Utilize AI to drive culinary innovation and healthier food design
Methodology- Training large language models on extensive culinary and ingredient datasets- Analyzing molecular interactions and flavor impact- Automating substitution suggestions balancing nutrition and taste
Key Achievements- Generated over 1,900 phytochemical-enriched ingredient combinations- Created more than 1,600 optimized recipes- Improved substitution prediction accuracy from ~35% to over 54%- Published findings in reputable scientific journals and conferences- Practical applications in menu innovation and health-focused gastronomy
Research TeamLuis Rita, Josh Southern, Ivan Laponogov, Kyle Higgins, Kirill Veselkov
ReferenceFull research paper available at: arXiv link

Optimizing Ingredient Substitution Using Large Language Models to Enhance Phytochemical Content in Recipes

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, DaVinci, and Meta's TinyLlama, using an ingredient substitution dataset. These models were used to predict substitutions that enhance phytochemical content and create a corresponding enriched recipe dataset. Our approach improved Hit@1 accuracy on ingredient substitution tasks, from the baseline 34.53 plus-minus 0.10% to 38.03 plus-minus 0.28% on the original GISMo dataset, and from 40.24 plus-minus 0.36% to 54.46 plus-minus 0.29% on a refined version of the same dataset. These substitutions led to the creation of 1,951 phytochemically enriched ingredient pairings and 1,639 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. Future work should include clinical validation and broader datasets to further evaluate the nutritional impact of these substitutions. This research represents a step forward in using AI to promote healthier eating practices, providing potential pathways for integrating computational methods with nutritional science.

Comments:15 pages
Subjects:Computation and Language (cs.CL)
Cite as:arXiv:2409.08792 [cs.CL]
 (or arXiv:2409.08792v1 [cs.CL] for this version)
 

https://doi.org/10.48550/arXiv.2409.08792

Submission history

From: Kirill Veselkov Dr [view email]
[v1] Fri, 13 Sep 2024 12:55:45 UTC (2,324 KB)