Abstract
Recent advances in large language models (LLMs) and the abundance of food data have resulted in studies to improve food understanding using LLMs. Despite several recommendation systems utilizing LLMs and Knowledge Graphs (KGs), there has been limited research on integrating food related KGs with LLMs. We introduce KERL, a unified system that leverages food KGs and LLMs to provide personalized food recommendations and generates recipes with associated micro-nutritional information. Given a natural language question, KERL extracts entities, retrieves subgraphs from the KG, which are then fed into the LLM as context to select the recipes that satisfy the constraints. Next, our system generates the cooking steps and nutritional information for each recipe. To evaluate our approach, we also develop a benchmark dataset by curating recipe related questions, combined with constraints and personal preferences. Through extensive experiments, we show that our proposed KG-augmented LLM significantly outperforms existing approaches, offering a complete and coherent solution for food recommendation, recipe generation, and nutritional analysis. Our code and benchmark datasets are publicly available at https://github.com/ mohbattharani/KERL . Give me low-protein recipes with baking soda, tomato paste, green onions, ground cinnamon, flour and without orange slice, sweet rice flour, yellow cake mix, and that include cholesterol within range (0, 0.07), salt per 100g within range (0.14, 0.26). 1. Aunt Peg's Banana Bread 2. Sweet Potato Casserole With Praline Topping 1. Aunt Peg's Banana Bread 2. Sweet Potato Casserole With Praline Topping 3. Fresh Apricot Praline Butter
Showing the abstract — retrieve the full paper via the Exa API.