Disparidades lingüísticas en el rendimiento de un modelo de lenguaje grande en preguntas dentales en siete idiomas
SAP Artificial Intelligence in Dentistry · 18.10.2026 · 2 · 158
DOI: 10.62486/aid2026158 ↗Kurz gefasst
Fachartikel in der Zeitschrift SAP Artificial Intelligence in Dentistry, online erschienen am 18.10.2026. Verfasst von Maikro Osvaldo Chávez Moya und 2 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Large language models answer dental questions, but their accuracy across languages has not been measured.
Methods
Sixty dental multiple-choice questions from MedMCQA were translated into Swahili, Hindi, Arabic, Chinese, Portuguese and Spanish with a fixed protocol and answered by the DeepSeek model at temperature zero, with English as the reference.
Results
Accuracy was 61.7% in English and 61.7% in Portuguese, and it fell to 60.0% in Chinese, 58.3% in Arabic and Spanish, 55.0% in Hindi, and 26.7% in Swahili. The English-to-language gap reached 6.7 percentage points for Hindi and 35.0 points for Swahili.
Conclusions
Accuracy held near the English reference in the high-resource European and Asian languages but collapsed in Swahili, so the language disparity in dental question answering is concentrated in the low-resource language rather than spread evenly across languages.
Zitieren
APA
Moya, M. O. C., Cabrera, L. H., & Ramos, N. P. (2026). Disparidades lingüísticas en el rendimiento de un modelo de lenguaje grande en preguntas dentales en siete idiomas. SAP Artificial Intelligence in Dentistry, 2, 158. https://doi.org/10.62486/aid2026158
Vancouver
Moya MOC, Cabrera LH, Ramos NP. Disparidades lingüísticas en el rendimiento de un modelo de lenguaje grande en preguntas dentales en siete idiomas. SAP Artificial Intelligence in Dentistry. 2026;2:158. doi:10.62486/aid2026158
BibTeX
@article{Moya2026,
author = {Moya, Maikro Osvaldo Chávez and Cabrera, Leodanis Hernández and Ramos, Neisy Pérez},
title = {Disparidades lingüísticas en el rendimiento de un modelo de lenguaje grande en preguntas dentales en siete idiomas},
journal = {SAP Artificial Intelligence in Dentistry},
year = {2026},
volume = {2},
pages = {158},
doi = {10.62486/aid2026158}
}
EUVIMED