Saved in:
Bibliographic Details
Main Authors: Lu, Linqi, Deng, Yifan, Tian, Chuan, Yang, Sijia, Shah, Dhavan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.14925
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917845161476096
author Lu, Linqi
Deng, Yifan
Tian, Chuan
Yang, Sijia
Shah, Dhavan
author_facet Lu, Linqi
Deng, Yifan
Tian, Chuan
Yang, Sijia
Shah, Dhavan
contents This study introduces Purrfessor, an innovative AI chatbot designed to provide personalized dietary guidance through interactive, multimodal engagement. Leveraging the Large Language-and-Vision Assistant (LLaVA) model fine-tuned with food and nutrition data and a human-in-the-loop approach, Purrfessor integrates visual meal analysis with contextual advice to enhance user experience and engagement. We conducted two studies to evaluate the chatbot's performance and user experience: (a) simulation assessments and human validation were conducted to examine the performance of the fine-tuned model; (b) a 2 (Profile: Bot vs. Pet) by 3 (Model: GPT-4 vs. LLaVA vs. Fine-tuned LLaVA) experiment revealed that Purrfessor significantly enhanced users' perceptions of care ($β= 1.59$, $p = 0.04$) and interest ($β= 2.26$, $p = 0.01$) compared to the GPT-4 bot. Additionally, user interviews highlighted the importance of interaction design details, emphasizing the need for responsiveness, personalization, and guidance to improve user engagement.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14925
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Purrfessor: A Fine-tuned Multimodal LLaVA Diet Health Chatbot
Lu, Linqi
Deng, Yifan
Tian, Chuan
Yang, Sijia
Shah, Dhavan
Human-Computer Interaction
Artificial Intelligence
This study introduces Purrfessor, an innovative AI chatbot designed to provide personalized dietary guidance through interactive, multimodal engagement. Leveraging the Large Language-and-Vision Assistant (LLaVA) model fine-tuned with food and nutrition data and a human-in-the-loop approach, Purrfessor integrates visual meal analysis with contextual advice to enhance user experience and engagement. We conducted two studies to evaluate the chatbot's performance and user experience: (a) simulation assessments and human validation were conducted to examine the performance of the fine-tuned model; (b) a 2 (Profile: Bot vs. Pet) by 3 (Model: GPT-4 vs. LLaVA vs. Fine-tuned LLaVA) experiment revealed that Purrfessor significantly enhanced users' perceptions of care ($β= 1.59$, $p = 0.04$) and interest ($β= 2.26$, $p = 0.01$) compared to the GPT-4 bot. Additionally, user interviews highlighted the importance of interaction design details, emphasizing the need for responsiveness, personalization, and guidance to improve user engagement.
title Purrfessor: A Fine-tuned Multimodal LLaVA Diet Health Chatbot
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2411.14925