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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Fan, Zhao, Xinjie, Xia, Ding, Zhou, Zhongyi, Yang, Rui, Lu, Jinghui, Jiang, Hang, Park, Chanjun, Li, Irene
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913801077522432
author Gao, Fan
Zhao, Xinjie
Xia, Ding
Zhou, Zhongyi
Yang, Rui
Lu, Jinghui
Jiang, Hang
Park, Chanjun
Li, Irene
author_facet Gao, Fan
Zhao, Xinjie
Xia, Ding
Zhou, Zhongyi
Yang, Rui
Lu, Jinghui
Jiang, Hang
Park, Chanjun
Li, Irene
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14594
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models
Gao, Fan
Zhao, Xinjie
Xia, Ding
Zhou, Zhongyi
Yang, Rui
Lu, Jinghui
Jiang, Hang
Park, Chanjun
Li, Irene
Human-Computer Interaction
Artificial Intelligence
Computation and Language
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.
title HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2504.14594