FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Tenghao, Lee, Donghee, Sweeney, John, Shi, Jiatong, Steliotes, Emily, Lange, Matthew, May, Jonathan, Chen, Muhao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912061810802688
author Huang, Tenghao
Lee, Donghee
Sweeney, John
Shi, Jiatong
Steliotes, Emily
Lange, Matthew
May, Jonathan
Chen, Muhao
author_facet Huang, Tenghao
Lee, Donghee
Sweeney, John
Shi, Jiatong
Steliotes, Emily
Lange, Matthew
May, Jonathan
Chen, Muhao
contents Flavor development in the food industry is increasingly challenged by the need for rapid innovation and precise flavor profile creation. Traditional flavor research methods typically rely on iterative, subjective testing, which lacks the efficiency and scalability required for modern demands. This paper presents three contributions to address the challenges. Firstly, we define a new problem domain for scientific agents in flavor science, conceptualized as the generation of hypotheses for flavor profile sourcing and understanding. To facilitate research in this area, we introduce the FoodPuzzle, a challenging benchmark consisting of 978 food items and 1,766 flavor molecules profiles. We propose a novel Scientific Agent approach, integrating in-context learning and retrieval augmented techniques to generate grounded hypotheses in the domain of food science. Experimental results indicate that our model significantly surpasses traditional methods in flavor profile prediction tasks, demonstrating its potential to transform flavor development practices.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12832
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists
Huang, Tenghao
Lee, Donghee
Sweeney, John
Shi, Jiatong
Steliotes, Emily
Lange, Matthew
May, Jonathan
Chen, Muhao
Computation and Language
Artificial Intelligence
Flavor development in the food industry is increasingly challenged by the need for rapid innovation and precise flavor profile creation. Traditional flavor research methods typically rely on iterative, subjective testing, which lacks the efficiency and scalability required for modern demands. This paper presents three contributions to address the challenges. Firstly, we define a new problem domain for scientific agents in flavor science, conceptualized as the generation of hypotheses for flavor profile sourcing and understanding. To facilitate research in this area, we introduce the FoodPuzzle, a challenging benchmark consisting of 978 food items and 1,766 flavor molecules profiles. We propose a novel Scientific Agent approach, integrating in-context learning and retrieval augmented techniques to generate grounded hypotheses in the domain of food science. Experimental results indicate that our model significantly surpasses traditional methods in flavor profile prediction tasks, demonstrating its potential to transform flavor development practices.
title FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.12832