Cross-Lingual Empirical Evaluation of Large Language Models for Arabic Medical Tasks
This addresses the problem of limited robustness in LLMs for linguistically diverse medical applications, highlighting incremental insights into language-specific performance issues.
The study tackled the performance gap of Large Language Models (LLMs) in Arabic versus English medical question answering, finding that the gap intensifies with task complexity and is linked to structural fragmentation in Arabic text and unreliable model confidence.
In recent years, Large Language Models (LLMs) have become widely used in medical applications, such as clinical decision support, medical education, and medical question answering. Yet, these models are often English-centric, limiting their robustness and reliability for linguistically diverse communities. Recent work has highlighted discrepancies in performance in low-resource languages for various medical tasks, but the underlying causes remain poorly understood. In this study, we conduct a cross-lingual empirical analysis of LLM performance on Arabic and English medical question and answering. Our findings reveal a persistent language-driven performance gap that intensifies with increasing task complexity. Tokenization analysis exposes structural fragmentation in Arabic medical text, while reliability analysis suggests that model-reported confidence and explanations exhibit limited correlation with correctness. Together, these findings underscore the need for language-aware design and evaluation strategies in LLMs for medical tasks.