.png){kind=icon}
.png){kind=icon}
Return
Evaluation of Large Language Models for Mapping Dietary Data to Food Databases
.png){kind=icon}
OA
AI
D
M
R
J
S
DOI：10.1016/j.tjnut.2026.101678.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
New food databases increasingly provide biochemical information not yet captured in standard food composition databases (FCDs). To enable precision nutrition, new methods are needed to map foods to these FCDs.
Keywords:
large language models
dietary intake
food composition databases
artificial intelligence
natural language processing
AI
artificial intelligence
ASA24
Automated Self-Administered 24-hr Dietary Assessment Tool
AMPM
Automated Multiple Pass Method
BERT
Bidirectional Encoder Representations from Transformers
DB
database
DFG2
Davis Food Glycopedia 2.0
EuroFIR
European Food Information Resource
FCD
Food Composition Database
FDA-FDD
Food and Drug Administration Food Disaggregation Database
FDC
FoodData Central
FNDDS
Food and Nutrient Database for Dietary Studies
GTE
General Text Embedding
INFOODS
International Network of Food Data Systems
LLMs
large language models
NDSR
Nutrition Data System for Research
NHANES
National Health and Nutrition Examination Survey
NLP
natural language processing
TF-IDF
term frequency-inverse document frequency
USDA
United States Department of Agriculture
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
T
IF:
0
Papers:
237
Citations:
0
Organization
Cited Papers