用大模型生成个性化餐单，精准匹配营养目标与实际饮食需求。
NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence
- 基于大模型和提示工程构建个性化营养数据库，融合美国农业部营养数据
- Llama 3.1 8B误差仅1.55%，接近用户设定热量目标
- 适合关注健康管理、想简化饮食规划的普通用户
维持均衡饮食对整体健康至关重要，但许多人因营养复杂、时间有限及饮食知识缺乏而难以规划餐食。个性化食物推荐可针对个人偏好、习惯和饮食限制定制餐单，但现有系统往往适应性差，忽略食材可得性等现实约束，且需大量用户输入，难以持续实用。为此，我们提出NutriGen框架，基于大语言模型（LLM）生成符合用户定义饮食偏好与限制的个性化餐单。通过构建个性化营养数据库并运用提示工程，使LLM能融入可靠的营养参考数据（如USDA营养数据库），同时保持灵活性与易用性。实验表明，LLMs在生成准确且用户友好的餐单方面潜力巨大，显著改善现有系统的结构化、实用性与可扩展性。评估显示，Llama 3.1 8B与GPT-3.5 Turbo分别实现1.55%和3.68%最低误差，餐单与用户设定热量目标高度一致，偏差小、精度高。此外，我们还对比了DeepSeek V3与其他成熟模型的性能，验证其在个性化营养规划中的应用潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。