Cross-Lingual Empirical Evaluation of Large Language Models for Arabic Medical Tasks

TL;DR

This paper empirically evaluates large language models on Arabic medical tasks, revealing a persistent language gap, tokenization issues, and limited reliability of model confidence, emphasizing the need for language-aware improvements.

Contribution

It provides the first comprehensive cross-lingual analysis of LLMs on Arabic medical tasks, highlighting performance gaps and underlying linguistic challenges.

Findings

Performance gap widens with task complexity.

Arabic tokenization shows structural fragmentation.

Model confidence and explanations have limited reliability.

Abstract

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.