Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models
This work addresses the problem of improving personalized nutrition through automated meal analysis, but it is incremental as it applies existing LLMs to a new domain.
This study evaluated three large language models (GPT-4o, Llama-3 70b, Mixtral 8x7b) for identifying and decomposing compound ingredients in meal plans, finding that while Llama-3 and GPT-4o excelled at decomposition, all models struggled with identifying essential elements like seasonings and oils.
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.