Authors : Swati Jakkan; Rupali Susar Patil; Shantanu Ekad; Pranjali Shinde

Volume/Issue : Volume 10 - 2025, Issue 3 - March

Google Scholar : https://tinyurl.com/3cj356rh

Scribd : https://tinyurl.com/e7dzftjv

DOI : https://doi.org/10.38124/ijisrt/25mar1460

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : The Recipe Generation and Ingredient Substitution System redefines the cooking experience by offering personalized recipe suggestions and intelligent ingredient substitutions tailored to user preferences, dietary needs, and available ingredients. Leveraging advanced Large Language Models (LLMs) integrated with Retrieval-Augmented Generation (RAG), the system processes natural language inputs to retrieve relevant recipes or generate customized recipes with precision. Its robust ingredient substitution mechanism evaluates alternatives through a scoring framework that considers flavor profiles, texture, functionality, and compatibility, ensuring that substitute ingredient maintain the dish’s integrity and quality. By incorporating flavor profile analysis, the system ensures substitutions preserve the harmony of tastes, enhancing both the quality and enjoyment of meals. The system is designed to empower novice and experienced cooks, the system transforms kitchen challenges into opportunities for exploration, enabling confident and innovative meal preparation.

Keywords : Recipe Generation, Ingredient Substitution, Large Language Models, (LLMs), Retrieval-Augmented Generation (RAG), Natural Language Processing (NLP).

References :

1. Lewis, Patrick, et al. "Retrieval-augmented generation for knowledge-intensive nlp tasks." Advances in Neural Information Processing Systems 33 (2020): 9459-9474.
2. Naveed, Humza, et al. "A comprehensive overview of large language models." arXiv preprint arXiv:2307.06435  (2023).
3. Mao, Xuehui, et al. "Recipe recommendation considering the flavor of regional cuisines." 2016 International conference on progress in informatics and computing (PIC). IEEE,     2016.
4. Razzaq, Muhammad Saad, et al. "EvoRecipes: a generative approach for evolving context-aware recipes." IEEE Access(2023).
5. Nadee, Wanvimol, and Sayan Unankard. "Alternative-ingredient recommendation based on correlation weight for thai recipes." 2021 joint international conference on digital arts, media and technology with ECTI northern section conference on electrical, electronics, computer and telecommunication engineering.          IEEE,     2021.
6. Shino, Naoki, Ryosuke Yamanishi, and Junichi Fukumoto. "Recommendation system for alternative-ingredients based on co-occurrence relation on recipe database and the ingredient category." 2016 5th IIAI international congress on advanced applied informatics (IIAI-AAI). IEEE, 2016.
7. Shirai, Sola S., et al. "Identifying ingredient substitutions using a knowledge graph of food." Frontiers in Artificial Intelligence 3 (2021): 621766.
8. Pellegrini,  Chantal,                et al. "Exploiting Food Embeddings for Ingredient Substitution." HEALTHINF 5 (2021): 67-77.
9. Yoshimaru, Naoki, et al. "Construction of Ingredient Embedding Considering Both Cooking Recipes and Their Ingredients." 2024 IEEE International Conference on Big Data and Smart               Computing (BigComp). IEEE, 2024.
10. Park, Donghyeon, et al. "FlavorGraph: a large-scale food-chemical graph for generating food representations and recommending food pairings." Scientific reports 11.1(2021):931.
11. Fatemi, Bahare, et al. "Learning to substitute ingredients in recipes." arXiv preprint                arXiv:2302.07960(2023).
12. Goel, Mansi, et al. "FlavorDB2: an updated database of flavor molecules."             Journal of Food Science (2024).
13. Rita, Luís, et al. "Optimizing ingredient substitution using large language models to enhance phytochemical content in recipes." Machine Learning and Knowledge Extraction 6.4 (2024): 2738-2752.
14. Haussmann, S. et al. (2019). FoodKG: A Semantics-Driven Knowledge Graph for Food Recommendation. In: Ghidini, C., et al. The Semantic Web – ISWC 2019. ISWC 2019. Lecture Notes in Computer Science(), vol 11779. Springer, Cham.
15. Ahn, Yong-Yeol, et al. "Flavor network and the principles of food pairing." Scientific reports 1.1 (2011): 196.
16. Sauer, Christopher, Alex Haigh, and Jake Rachleff. "Cooking up food embeddings." (2017)
17. Sozuer Zorlu, Sibel, Oded Netzer, and Kriste Krstovski. "A Recipe for Creating Recipes: An Ingredient Embedding Approach." Available at SSRN 4686749 (2024).