Our approach achieved top performance across all three subtasks of the MEDIQA-CORR 2024 shared task, demonstrating the effectiveness of LLM-based programs in detecting, localizing, and correcting medical errors in clinical text.
This paper presents a multi-agent framework called MedReAct'N'MedReFlex that leverages large language models and retrieval-augmented generation to tackle the task of medical error detection and correction in clinical notes.