Large Language Models Applied to Controlled Natural Languages in Communicating Diabetes Therapies

Federica Vezzani, Sara Vecchiato, Elena Frattolin


Abstract
The aim of this exploratory study is to test the possibility of enhancing the quality of institutional communication related to diabetes self-treatment by switching from manual to prompt-based writing. The study proposes an investigation into the use of prompts applied to controlled natural language, particularly in Italian, French and English. Starting from a corpus of three comparable texts concerning the so-called Rule of 15, a reformulation is undertaken in accordance with the principles of controlled natural languages. Feedback will be gathered through a Likert scale questionnaire and a comprehension test administered to anonymous volunteers.
Anthology ID:
2025.aielpl-1.3
Volume:
Proceedings of the 1st Workshop on Artificial Intelligence and Easy and Plain Language in Institutional Contexts (AI & EL/PL)
Month:
June
Year:
2025
Address:
Geneva, Switzerland
Editors:
María Isabel Rivas Ginel, Patrick Cadwell, Paolo Canavese, Silvia Hansen-Schirra, Martin Kappus, Anna Matamala, Will Noonan
Venue:
AIELPL
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
25–29
Language:
URL:
https://preview.aclanthology.org/mtsummit-25-ingestion/2025.aielpl-1.3/
DOI:
Bibkey:
Cite (ACL):
Federica Vezzani, Sara Vecchiato, and Elena Frattolin. 2025. Large Language Models Applied to Controlled Natural Languages in Communicating Diabetes Therapies. In Proceedings of the 1st Workshop on Artificial Intelligence and Easy and Plain Language in Institutional Contexts (AI & EL/PL), pages 25–29, Geneva, Switzerland. European Association for Machine Translation.
Cite (Informal):
Large Language Models Applied to Controlled Natural Languages in Communicating Diabetes Therapies (Vezzani et al., AIELPL 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/mtsummit-25-ingestion/2025.aielpl-1.3.pdf