KERL：基於大型語言模型的知識增強型個性化食譜推薦系統

KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models

May 20, 2025

作者: Fnu Mohbat, Mohammed J Zaki

cs.AI

摘要

近期大型語言模型（LLMs）的進展以及豐富的食品數據，促進了利用LLMs提升食品理解的研究。儘管已有數個推薦系統結合了LLMs與知識圖譜（KGs），但將食品相關的KGs與LLMs整合的研究仍有限。我們提出了KERL，這是一個統一系統，它利用食品KGs和LLMs來提供個性化的食品推薦，並生成附帶微量營養信息的食譜。給定一個自然語言問題，KERL會提取實體，從KG中檢索子圖，然後將這些子圖作為上下文輸入LLM，以選擇滿足約束條件的食譜。接著，我們的系統會為每個食譜生成烹飪步驟和營養信息。為了評估我們的方法，我們還開發了一個基準數據集，通過整理與食譜相關的問題，結合約束條件和個人偏好。通過大量實驗，我們展示了我們提出的KG增強型LLM顯著優於現有方法，為食品推薦、食譜生成和營養分析提供了一個完整且連貫的解決方案。我們的代碼和基準數據集公開於https://github.com/mohbattharani/KERL。

English

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.