HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models

2025-04-20

AI Summary

Personalized healthy diet guidance suffers from high user interaction burden, excessive cognitive load, and insufficient explanation and visualization. Method: This paper proposes HealthGenie—a novel system integrating knowledge graphs (KGs) and large language models (LLMs). KGs provide structured, traceable nutritional knowledge to ensure interpretability, while LLMs enable natural-language dialogue, collaborative query optimization, category-aware retrieval, and stepwise reasoning. HealthGenie further introduces an interactive hierarchical visualization interface supporting dynamic preference tuning and progressive unfolding of recommendation logic. Contribution/Results: In a within-subject study with 12 participants, HealthGenie significantly reduced cognitive load and interaction steps, while improving recommendation personalization and user trust. The results validate a new paradigm wherein KG-driven explainability and LLM-powered interactivity synergistically enhance the efficacy of digital health interventions.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Intelligent User Interfaces
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Seeking dietary guidance often requires navigating complex professional knowledge while accommodating individual health conditions. Knowledge Graphs (KGs) offer structured and interpretable nutritional information, whereas Large Language Models (LLMs) naturally facilitate conversational recommendation delivery. In this paper, we present HealthGenie, an interactive system that combines the strengths of LLMs and KGs to provide personalized dietary recommendations along with hierarchical information visualization for a quick and intuitive overview. Upon receiving a user query, HealthGenie performs query refinement and retrieves relevant information from a pre-built KG. The system then visualizes and highlights pertinent information, organized by defined categories, while offering detailed, explainable recommendation rationales. Users can further tailor these recommendations by adjusting preferences interactively. Our evaluation, comprising a within-subject comparative experiment and an open-ended discussion, demonstrates that HealthGenie effectively supports users in obtaining personalized dietary guidance based on their health conditions while reducing interaction effort and cognitive load. These findings highlight the potential of LLM-KG integration in supporting decision-making through explainable and visualized information. We examine the system's usefulness and effectiveness with an N=12 within-subject study and provide design considerations for future systems that integrate conversational LLM and KG.

Problem

• Provides personalized dietary recommendations using KG and LLM
• Reduces interaction effort and cognitive load for users
• Combines structured KG data with conversational LLM delivery

Innovation

• Combines Knowledge Graphs and Large Language Models
• Provides personalized dietary recommendations interactively
• Visualizes hierarchical information for quick overview