Integrating Expertise in LLMs: Crafting a Customized Nutrition Assistant with Refined Template Instructions

要旨

Large Language Models (LLMs) have the potential to contribute to the fields of nutrition and dietetics in generating food product explanations that facilitate informed food selections. However, the extent to which these models offer effective and accurate information remains unverified. In collaboration with registered dietitians (RDs), we evaluate the strengths and weaknesses of LLMs in providing accurate and personalized nutrition information. Through a mixed-methods approach, RDs validated GPT-4 outputs at various levels of prompt specificity, which led to the development of design guidelines used to prompt LLMs for nutrition information. We tested these guidelines by creating a GPT prototype, The Food Product Nutrition Assistant, tailored for food product explanations. This prototype was refined and evaluated in focus groups with RDs. We find that the implementation of these dietitian-reviewed template instructions enhance the generation of detailed food product descriptions and tailored nutrition information.

著者
Annalisa Szymanski
University of Notre Dame, South Bend, Indiana, United States
Brianna L. Wimer
University of Notre Dame, South Bend, Indiana, United States
Oghenemaro Anuyah
University of Notre Dame, Notre Dame, Indiana, United States
Heather Eicher-Miller
Purdue University, West Lafayette, Indiana, United States
Ronald Metoyer
University of Notre Dame, South Bend, Indiana, United States
論文URL

https://doi.org/10.1145/3613904.3641924

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Wellbeing and Eating: Nutrition and Weight

324
5 件の発表
2024-05-14 01:00:00
2024-05-14 02:20:00