20.500.12556/DKUM-92722 Improving personalized meal planning with large language models: identifying and decomposing compound ingredients Background/Objectives: Identifying and decomposing compound ingredients within meal plans presents meal customization and nutritional analysis challenges. It is essential for accurately identifying and replacing problematic ingredients linked to allergies or intolerances and helping nutritional evaluation. Methods: This study explored the effectiveness of three large language models (LLMs)—GPT-4o, Llama-3 (70B), and Mixtral (8x7B), in decomposing compound ingredients into basic ingredients within meal plans. GPT-4o was used to generate 15 structured meal plans, each containing compound ingredients. Each LLM then identified and decomposed these compound items into basic ingredients. The decomposed ingredients were matched to entries in a subset of the USDA FoodData Central repository using API-based search and mapping techniques. Nutritional values were retrieved and aggregated to evaluate accuracy of decomposition. Performance was assessed through manual review by nutritionists and quantified using accuracy and F1-score. Statistical significance was tested using paired t-tests or Wilcoxon signed-rank tests based on normality. Results: Results showed that large models—both Llama-3 (70B) and GPT-4o—outperformed Mixtral (8x7B), achieving average F1-scores of 0.894 (95% CI: 0.84–0.95) and 0.842 (95% CI: 0.79–0.89), respectively, compared to an F1-score of 0.690 (95% CI: 0.62–0.76) from Mixtral (8x7B). Conclusions: 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. artificial intelligence food analysis LLM Ilama GPT mixtral ingredient identification ingredient decomposition personalized nutrition meal customization nutritional analysis dietary planning umetna inteligenca analiza hrane LLM Ilama GPT mixtral prepoznavanje sestavin razčlenjevanje sestavin personalizirana prehrana prilagoditev obrokov nutricionistična analiza načrtovanje prehrane true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/nutrients © 2025 by the authors Znanstveno delo 2025-05-08 09:26:40 2025-05-08 13:51:39 2025-07-21 10:56:15 0000-00-00 00:00:00 2025 0 0 Str. 1-15 št. 9, št. članka 1492 Letn. 17 2025 0000-00-00 Zaloznikova Objavljeno apc 2025-03-25 2025-04-18 2025-04-29 004.89:613.2 235011587 10.3390/nu17091492 2072-6643 nutrients-17-01492.pdf nutrients-17-01492.pdf 1 BF0D9BB177BE275EAB7EF59CDC27A42F 6a599a2b7c7ece79601cc9f746694b019bde99931b74750a1bfe13af9535fe67 e23a4825-2bdd-11f0-98aa-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=190784 https://www.mdpi.com/2072-6643/17/9/1492 1 c8bb8987-2bdd-11f0-98aa-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=190783 Fakulteta za zdravstvene vede Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0