This research proposes a novel approach to scale medical LLMs to 50 languages by leveraging a Mixture of Language Family Experts within a Post-MoE architecture, effectively addressing the challenge of data scarcity in low-resource languages and democratizing access to medical information globally.
개발된 Apollo은 61억 인구를 대상으로 하는 최첨단 다국어 의료 LLMs를 제공합니다.
医療AIの民主化を目指すための軽量多言語医療LLMの開発とその効果的な利用方法に焦点を当てる。
The author aims to democratize medical AI by developing multilingual LLMs to reach a global population of 6.1 billion, enhancing healthcare accessibility.