[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-401962-105":59,"doc-detail-401962-en":135},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":128,"head_meta":130,"extra_data":132,"updated_unix":134},105,"en","nutrigen-personalized-meal-plan-generator-leveraging-large-language-models-to-enhance-dietary-and-nutritional-adherence","NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence","","Maintaining a balanced diet is essential for health, yet meal planning is difficult for many people due to nutritional complexity, limited time, and insufficient dietary knowledge. NutriGen is introduced as an LLM-based framework that generates personalized meal plans aligned with user preferences, habits, and constraints. It builds a personalized nutrition database and uses prompt engineering to reference reliable sources such as the USDA nutrition database. Experiments show Llama 3.1 8B and GPT-3.5 Turbo achieve the lowest error rates (1.55% and 3.68%) while matching caloric targets accurately. The study also evaluates DeepSeek V3, finding higher MAE (10.45%) and slower processing, indicating optimization needs.",{"@graph":69,"@context":127},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/nutrigen-personalized-meal-plan-generator-leveraging-large-language-models-to-enhance-dietary-and-nutritional-adherence/401962/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/nutrigen-personalized-meal-plan-generator-leveraging-large-language-models-to-enhance-dietary-and-nutritional-adherence/401962.png","ImageObject",300,407,{"name":92,"@type":93},"WPS_1786070896","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-03","2026-09-27",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119,123],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does NutriGen target in meal planning?","Question",{"text":113,"@type":114},"NutriGen targets difficulties in maintaining a balanced diet caused by nutritional complexity, time constraints, and lack of dietary knowledge, especially when systems cannot adapt to real-world constraints and user requirements.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does NutriGen generate personalized meal plans?",{"text":118,"@type":114},"It uses large language models with a personalized nutrition database and prompt engineering so the model can incorporate reliable references such as the USDA nutrition database while staying flexible to user-defined preferences and constraints.",{"name":120,"@type":111,"acceptedAnswer":121},"Which models performed best in the evaluation and how?",{"text":122,"@type":114},"Llama 3.1 8B and GPT-3.5 Turbo achieved the lowest percentage errors (1.55% and 3.68%), producing meal plans that closely match user caloric targets with minimal deviation.",{"name":124,"@type":111,"acceptedAnswer":125},"What were DeepSeek V3’s results compared with other models?",{"text":126,"@type":114},"DeepSeek V3 struggled with accuracy, showing a higher MAE of 10.45%, and it was significantly slower than models like GPT-3.5 Turbo and Llama 3.1 8B, suggesting further optimization is needed.","https://schema.org",{"og:url":83,"og:type":129,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":131,"canonical":83},"index,follow",{"doc_id":133,"site_id":62},401962,1790903514,{"code":4,"msg":5,"data":136},{"doc_id":133,"user_id":137,"nickname":92,"user_avatar":138,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":139,"file_id":140,"file_url":141,"file_type":142,"file_size":143,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":34,"language":144,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":67,"update_tm":148,"read_time":149,"preview_page_count":4},549768072016,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence  \nSaman Khamesian 1 ,2 , Asiful Arefeen 1 ,2 , Stephanie M. Carpenter1 , and Hassan Ghasemzadeh 1  \narXiv :2502 .20601v2 [ cs .AI] 28 Apr 2025  \nAbstract—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. Our results showed that it struggled with accuracy, exhibiting a higher MAE of 10.45%, and was significantly slower in processing time compared to models like GPT-3.5 Turbo and Llama 3.1 8B, highlighting the need for further optimization.  \nIndex Terms—personalized food recommendation, diet, large language models, prompt engineering, AI, machine learning, eHealth, behavioral health.  \nI. INTRODUCTION  \nMaintaining a healthy diet is fundamental to preventing and managing a range of chronic diseases, including obesity, cardiovascular conditions, and diabetes [1] . Despite its importance, many individuals face significant challenges in adhering to a healthy eating regimen. These difficulties often stem from the need to calculate daily caloric intake, evaluate the nutritional value of meals, and consistently make informed decisions about what to eat. Additionally, planning balanced meal schedules or preparing meals with the ingredients available at home can be overwhelming,  \n1College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA.  \n2 School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, USA.  \nCorresponding author: [skhamesi@asu.edu](skhamesi@asu.edu)  \nespecially when trying to align with specific dietary goals and restrictions. These barriers highlight the pressing need for tools that simplify these decision making processes, making it easier for individuals to adopt and sustain healthier eating habits over time [2] .  \nTo address the aforementioned challenges, personalized dietary recommendation systems have emerged as a promising solution. Unlike conventional food recommendation systems, which primarily consider whether users enjoy specific foods, personalized approaches cater to both individual dietary preferences and health needs, such as gluten-free diets, allergy sensitivities, and vegetarian lifestyles [3] . These systems aim to meet unique nutritional requirements, ensuring better adherence and promoting long-term health outcomes [4],","cbCail4gaSm7PABJ","https://ap.wps.com/l/cbCail4gaSm7PABJ","pdf",1440271,"English","# Introduction\n## Personalized dietary recommendation systems\n## Prior approaches and machine learning methods\n## Limitations of existing systems","[{\"question\":\"What problem does NutriGen target in meal planning?\",\"answer\":\"NutriGen targets difficulties in maintaining a balanced diet caused by nutritional complexity, time constraints, and lack of dietary knowledge, especially when systems cannot adapt to real-world constraints and user requirements.\"},{\"question\":\"How does NutriGen generate personalized meal plans?\",\"answer\":\"It uses large language models with a personalized nutrition database and prompt engineering so the model can incorporate reliable references such as the USDA nutrition database while staying flexible to user-defined preferences and constraints.\"},{\"question\":\"Which models performed best in the evaluation and how?\",\"answer\":\"Llama 3.1 8B and GPT-3.5 Turbo achieved the lowest percentage errors (1.55% and 3.68%), producing meal plans that closely match user caloric targets with minimal deviation.\"},{\"question\":\"What were DeepSeek V3’s results compared with other models?\",\"answer\":\"DeepSeek V3 struggled with accuracy, showing a higher MAE of 10.45%, and it was significantly slower than models like GPT-3.5 Turbo and Llama 3.1 8B, suggesting further optimization is needed.\"}]","NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence | PDF",1790525691,18]