# From "What to Eat?" to Perfect Recipe: ChefMind's Chain-of-Exploration for Ambiguous User Intent in Recipe Recommendation

arXiv: https://arxiv.org/abs/2509.18226 · HTML: https://mlsanity.com/paper/2509.18226/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [Searching for Best Practices in Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01219/) (2024)
- [Food Recommendation: Framework, Existing Solutions and Challenges](https://mlsanity.com/paper/1905.06269/) (2019)
- [Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph](https://mlsanity.com/paper/2101.01775/) (2021)
- [Applications of knowledge graphs for food science and industry](https://mlsanity.com/paper/2107.05869/) (2021)
- [Personalized, Health-Aware Recipe Recommendation: An Ensemble Topic Modeling Based Approach](https://mlsanity.com/paper/1908.00148/) (2019)
- [KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models](https://mlsanity.com/paper/2505.14629/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Raw Features to Effective Embeddings: A Three-Stage Approach for Multimodal Recipe Recommendation](https://mlsanity.com/paper/2511.19176/) (2025)

## Abstract (arXiv)

Personalized recipe recommendation faces challenges in handling fuzzy user intent, ensuring semantic accuracy, and providing sufficient detail coverage. We propose ChefMind, a hybrid architecture combining Chain of Exploration (CoE), Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM). CoE refines ambiguous queries into structured conditions, KG offers semantic reasoning and interpretability, RAG supplements contextual culinary details, and LLM integrates outputs into coherent recommendations. We evaluate ChefMind on the Xiachufang dataset and manually annotated queries, comparing it with LLM-only, KG-only, and RAG-only baselines. Results show that ChefMind achieves superior performance in accuracy, relevance, completeness, and clarity, with an average score of 8.7 versus 6.4-6.7 for ablation models. Moreover, it reduces unprocessed queries to 1.6%, demonstrating robustness in handling fuzzy demands.