Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models

TL;DR

This paper evaluates large language models' ability to identify and decompose complex ingredients in meal plans, highlighting their strengths and limitations for personalized nutrition applications.

Contribution

It systematically assesses multiple LLMs' performance in ingredient decomposition, revealing their potential and current challenges in meal planning tasks.

Findings

Llama-3 and GPT-4o excel in ingredient decomposition

Models struggle with identifying seasonings and oils

Performance varies across different models

Abstract

This study explores the effectiveness of Large Language Models in meal planning, focusing on their ability to identify and decompose compound ingredients. We evaluated three models-GPT-4o, Llama-3 (70b), and Mixtral (8x7b)-to assess their proficiency in recognizing and breaking down complex ingredient combinations. Preliminary results indicate that while Llama-3 (70b) and GPT-4o excels in accurate decomposition, all models encounter difficulties with identifying essential elements like seasonings and oils. Despite strong overall performance, variations in accuracy and completeness were observed across models. These findings underscore LLMs' potential to enhance personalized nutrition but highlight the need for further refinement in ingredient decomposition. Future research should address these limitations to improve nutritional recommendations and health outcomes.