Multilingual Medical Reasoning for Question Answering with Large Language Models

ArXi:2512.05658v2 Announce Type: replace-cross Large Language Models (LLMs) with reasoning capabilities have recently nstrated strong potential in medical Question Answering (QA). Existing approaches are largely English-focused and primarily rely on distillation from general-purpose LLMs, raising concerns about the reliability of their medical knowledge. In this work, we present a method to generate multilingual reasoning traces based on medical knowledge extracted from Wikipedia.