一作ACL 2026Poster· Natural Language Processing
CURE - M ed: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning
Eric Onyame · Akash Ghosh · Subhadip Baidya · Sriparna Saha · Xiuying Chen · Chirag Agarwal
摘要
While large language models (LLMs) have shown to perform well on monolingual mathematical and commonsense reasoning, they remain unreliable for multilingual medical reasoning applications, hindering their deployment in multilingual healthcare settings. We address this by first introducing CURE-Me...