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

arXiv: https://arxiv.org/abs/2505.14629 · HTML: https://mlsanity.com/paper/2505.14629/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 59 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering](https://mlsanity.com/paper/2404.17723/) (2024)
- [Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food](https://mlsanity.com/paper/2103.03375/) (2021)
- [RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System](https://mlsanity.com/paper/2003.02498/) (2020)
- [FoodLMM: A Versatile Food Assistant using Large Multi-modal Model](https://mlsanity.com/paper/2312.14991/) (2023)
- [SPARQL Generation: an analysis on fine-tuning OpenLLaMA for Question Answering over a Life Science Knowledge Graph](https://mlsanity.com/paper/2402.04627/) (2024)
- [DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph](https://mlsanity.com/paper/2303.13351/) (2023)
- [FIRE: Food Image to REcipe generation](https://mlsanity.com/paper/2308.14391/) (2023)
- [MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation](https://mlsanity.com/paper/2412.08847/) (2024)
- [Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph](https://mlsanity.com/paper/2101.01775/) (2021)
- [FoodGPT: A Large Language Model in Food Testing Domain with Incremental Pre-training and Knowledge Graph Prompt](https://mlsanity.com/paper/2308.10173/) (2023)
- [LLaVA-Chef: A Multi-modal Generative Model for Food Recipes](https://mlsanity.com/paper/2408.16889/) (2024)
- [Leveraging LLMs in Scholarly Knowledge Graph Question Answering](https://mlsanity.com/paper/2311.09841/) (2023)
- [CaLoRAify: Calorie Estimation with Visual-Text Pairing and LoRA-Driven Visual Language Models](https://mlsanity.com/paper/2412.09936/) (2024)
- [Monte Carlo Tree Search for Recipe Generation using GPT-2](https://mlsanity.com/paper/2401.05199/) (2024)
- [KaPQA: Knowledge-Augmented Product Question-Answering](https://mlsanity.com/paper/2407.16073/) (2024)
- [Food Recommendation as Language Processing (F-RLP): A Personalized and Contextual Paradigm](https://mlsanity.com/paper/2402.07477/) (2024)

## Built on by (most cited first, 2 of 2)

- [From "What to Eat?" to Perfect Recipe: ChefMind's Chain-of-Exploration for Ambiguous User Intent in Recipe Recommendation](https://mlsanity.com/paper/2509.18226/) (2025)
- [Quantifying Hidden Salt for Precision Healthcare: Sodium Assessment via Joint-Factor Retrieval and Chain-of-Thought Inference](https://mlsanity.com/paper/2609.22171/) (2026)

## Abstract (arXiv)

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.