Error Detection in Medical Note through Multi Agent Debate

Large Language Models (LLMs) have approached human-level performance in text generation and summarization, yet their application in clinical settings remains constrained by potential inaccuracies that could lead to serious consequences.This work addresses the critical safety weaknesses in medical documentation systems by focusing on detecting subtle errors that require specialized medical expertise.We introduce a novel multi-agent debating framework that achieves 78.8% accuracy on medical error detection, significantly outperforming both single-agent approaches and previous multi-agent systems.Our framework leverages specialized LLM agents with asymmetric access to complementary medical knowledge sources (Mayo Clinic and WebMD), engaging them in structured debate to identify inaccuracies in clinical notes.A judge agent evaluates these arguments based solely on their medical reasoning quality, with agent-specific performance metrics incorporated as feedback for developing situation-specific trust models.This research significantly enhances the safety and reliability of automated medical documentation, potentially facilitating wider AI adoption in healthcare while maintaining high standards of accuracy.The performance gap between individual specialized agents (WebMD: 70.2%, Mayo: 72.6%) compared to their combined implementation demonstrates the synergistic value of integrating complementary clinical perspectives through structured debate.