| Title: | Large language models in food and nutrition science : opportunities, challenges, and the case of FoodyLLM |
|---|
| Authors: | ID Gjorgjevikj, Ana, Institut "Jožef Stefan" (Author)
ID Martinc, Matej, Institut "Jožef Stefan" (Author)
ID Cenikj, Gjorgjina, Institut "Jožef Stefan" (Author)
ID Drole, Jan, Institut "Jožef Stefan" (Author)
ID Ogrinc, Nives, Institut "Jožef Stefan" (Author)
ID Džeroski, Sašo, Institut "Jožef Stefan" (Author)
ID Koroušić-Seljak, Barbara, Institut "Jožef Stefan" (Author)
ID Eftimov, Tome, Institut "Jožef Stefan" (Author), et al. |
|---|
| Files: |  URL - Source URL, visit https://www.sciencedirect.com/science/article/pii/S2665927126000511?via%3Dihub
 PDF - Presentation file, download (6,37 MB)
MD5: B15A5C3391C3B2DF6F3C98B691CC9D4E
Description: Raziskovalni podatki so na voljo na straneh https://github.com/matejMartinc/FoodyLLM, https://huggingface.co/Matej/FoodyLLM in https://zenodo.org/records/17798877.
|
|---|
| Language: | English |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: |  IJS - Jožef Stefan Institute
|
|---|
| Abstract: | Background Reliable nutrient profiling and semantic interoperability are essential for scalable dietary assessment, food labeling (e.g., traffic-light schemes), and FAIR integration of food composition and consumption data. However, general-purpose large language models (LLMs) are not systematically exposed to structured recipe–nutrition mappings and food ontologies, limiting their accuracy and trustworthiness in food and nutrition tasks. Scope and approach We review recent LLM advances in life sciences and healthcare and analyze the gap in food and nutrition applications. To address this gap, we introduce FoodyLLM, a domain-specialized LLM fine-tuned on 225k task-aligned QA pairs for (i) recipe nutrient estimation, (ii) traffic-light classification, and (iii) ontology-based entity linking to support FAIR food data interoperability. We benchmark FoodyLLM against strong general-purpose baselines (e.g., Llama 3 8B, Gemini 2.0) under zero-/few-shot prompting across five evaluation folds. Key findings Across all tasks, FoodyLLM substantially outperforms general-purpose LLMs for nutrient estimation across all macronutrients (fat, protein, salt, saturates, sugar), accuracy increases from 0.43 to 0.63 to 0.91–0.97; for traffic-light classification across all nutrients and color categories, macro F1 improves from 0.46 to 0.80 to 0.86–0.97; and for ontology-based food entity linking across FoodOn, SNOMED-CT, and Hansard, macro F1 increases from 0.33 to 0.44 (best general-purpose baseline) to 0.93–0.98 on artificial NEL data, and from 0.24 to 0.51 to 0.67–0.84 on real corpora (CafeteriaSA and CafeteriaFCD). Overall, our results demonstrate the practical value of domain-specialized LLMs in food and nutrition research. They enable automated dietary assessment, large-scale nutritional monitoring, and FAIR data integration, while opening new pathways toward sustainable and personalized nutrition. |
|---|
| Keywords: | FoodyLLM, nutrient estimation, data interoperability |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 13.11.2025 |
|---|
| Article acceptance date: | 13.02.2026 |
|---|
| Publication date: | 16.02.2026 |
|---|
| Publisher: | Elsevier |
|---|
| Year of publishing: | 2026 |
|---|
| Number of pages: | str. 1-26 |
|---|
| Numbering: | Vol. 12, [article no.] 101351 |
|---|
| Source: | Nizozemska |
|---|
| PID: | 20.500.12556/DiRROS-27977  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 2665-9271 |
|---|
| DOI: | 10.1016/j.crfs.2026.101351 |
|---|
| COBISS.SI-ID: | 270414595 |
|---|
| Copyright: | © 2026 The Authors. |
|---|
| Note: | Nasl. z nasl. zaslona;
Soavtorji: Matej Martinc, Gjorgjina Venikj, Jan Drole, Nives Ogrinc, Sašo Džeroski, Barbara Koroušić Seljak, Tome Eftimov;
Opis vira z dne 4. 3. 2026;
|
|---|
| Publication date in DiRROS: | 04.03.2026 |
|---|
| Views: | 41 |
|---|
| Downloads: | 19 |
|---|
| Metadata: |    |
|---|
|
:
|
Copy citation |
|---|
| | | | Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
