Salvato in:
Dettagli Bibliografici
Autori principali: Hua, Andong, Dhaliwal, Mehak Preet, Pullela, Laya, Burke, Ryan, Qin, Yao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.12843
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918367671091200
author Hua, Andong
Dhaliwal, Mehak Preet
Pullela, Laya
Burke, Ryan
Qin, Yao
author_facet Hua, Andong
Dhaliwal, Mehak Preet
Pullela, Laya
Burke, Ryan
Qin, Yao
contents Accurate nutrition estimation helps people make informed dietary choices and is essential in the prevention of serious health complications. We present NutriBench, the first publicly available natural language meal description nutrition benchmark. NutriBench consists of 11,857 meal descriptions generated from real-world global dietary intake data. The data is human-verified and annotated with macro-nutrient labels, including carbohydrates, proteins, fats, and calories. We conduct an extensive evaluation of NutriBench on the task of carbohydrate estimation, testing twelve leading Large Language Models (LLMs), including GPT-4o, Llama3.1, Qwen2, Gemma2, and OpenBioLLM models, using standard, Chain-of-Thought and Retrieval-Augmented Generation strategies. Additionally, we present a study involving professional nutritionists, finding that LLMs can provide comparable but significantly faster estimates. Finally, we perform a real-world risk assessment by simulating the effect of carbohydrate predictions on the blood glucose levels of individuals with diabetes. Our work highlights the opportunities and challenges of using LLMs for nutrition estimation, demonstrating their potential to aid professionals and laypersons and improve health outcomes. Our benchmark is publicly available at: https://mehak126.github.io/nutribench.html
format Preprint
id arxiv_https___arxiv_org_abs_2407_12843
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions
Hua, Andong
Dhaliwal, Mehak Preet
Pullela, Laya
Burke, Ryan
Qin, Yao
Computation and Language
Artificial Intelligence
Accurate nutrition estimation helps people make informed dietary choices and is essential in the prevention of serious health complications. We present NutriBench, the first publicly available natural language meal description nutrition benchmark. NutriBench consists of 11,857 meal descriptions generated from real-world global dietary intake data. The data is human-verified and annotated with macro-nutrient labels, including carbohydrates, proteins, fats, and calories. We conduct an extensive evaluation of NutriBench on the task of carbohydrate estimation, testing twelve leading Large Language Models (LLMs), including GPT-4o, Llama3.1, Qwen2, Gemma2, and OpenBioLLM models, using standard, Chain-of-Thought and Retrieval-Augmented Generation strategies. Additionally, we present a study involving professional nutritionists, finding that LLMs can provide comparable but significantly faster estimates. Finally, we perform a real-world risk assessment by simulating the effect of carbohydrate predictions on the blood glucose levels of individuals with diabetes. Our work highlights the opportunities and challenges of using LLMs for nutrition estimation, demonstrating their potential to aid professionals and laypersons and improve health outcomes. Our benchmark is publicly available at: https://mehak126.github.io/nutribench.html
title NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.12843