NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence

2025-02-28

AI Summary

Existing dietary recommendation systems exhibit poor adaptability, struggle to accommodate real-world constraints (e.g., ingredient availability), and rely heavily on extensive user input—limiting their sustainability and practical deployment. NutriGen addresses these challenges by proposing an LLM-based personalized meal planning framework that deeply integrates Llama 3.1 8B, GPT-3.5 Turbo, and DeepSeek V3 into a closed-loop nutritional planning pipeline. Leveraging prompt engineering, a custom-built personalized nutrition knowledge base, and the USDA’s authoritative food composition database, NutriGen enables preference-driven, constraint-aware menu generation. It introduces the first native LLM adaptation to nutritional planning tasks, ensuring scientific rigor while substantially reducing user burden. Experimental results demonstrate that Llama 3.1 8B achieves a minimal calorie deviation error of 1.55%, significantly outperforming baseline methods. These findings validate NutriGen’s advances in accuracy, practicality, and scalability.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Maintaining a balanced diet is essential for overall health, yet many individuals struggle with meal planning due to nutritional complexity, time constraints, and lack of dietary knowledge. Personalized food recommendations can help address these challenges by tailoring meal plans to individual preferences, habits, and dietary restrictions. However, existing dietary recommendation systems often lack adaptability, fail to consider real-world constraints such as food ingredient availability, and require extensive user input, making them impractical for sustainable and scalable daily use. To address these limitations, we introduce NutriGen, a framework based on large language models (LLM) designed to generate personalized meal plans that align with user-defined dietary preferences and constraints. By building a personalized nutrition database and leveraging prompt engineering, our approach enables LLMs to incorporate reliable nutritional references like the USDA nutrition database while maintaining flexibility and ease-of-use. We demonstrate that LLMs have strong potential in generating accurate and user-friendly food recommendations, addressing key limitations in existing dietary recommendation systems by providing structured, practical, and scalable meal plans. Our evaluation shows that Llama 3.1 8B and GPT-3.5 Turbo achieve the lowest percentage errors of 1.55% and 3.68%, respectively, producing meal plans that closely align with user-defined caloric targets while minimizing deviation and improving precision. Additionally, we compared the performance of DeepSeek V3 against several established models to evaluate its potential in personalized nutrition planning.

Problem

• Generates personalized meal plans using large language models.
• Addresses limitations in existing dietary recommendation systems.
• Improves accuracy and user-friendliness of food recommendations.

Innovation

• Leverages large language models for personalized meal plans
• Integrates USDA nutrition database via prompt engineering
• Achieves low error rates with Llama 3.1 and GPT-3.5