Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912112967680000 |
|---|---|
| author | Kopitar, Leon Bedrac, Leon Strath, Larissa J Bian, Jiang Stiglic, Gregor |
| author_facet | Kopitar, Leon Bedrac, Leon Strath, Larissa J Bian, Jiang Stiglic, Gregor |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05892 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models Kopitar, Leon Bedrac, Leon Strath, Larissa J Bian, Jiang Stiglic, Gregor Computation and Language Artificial Intelligence Information Retrieval 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. |
| title | Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2411.05892 |