辩证-调解：通过反事实对抗多智能体辩论缓解诊断幻觉
Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate
AI总结：
本文提出Dialectic-Med框架，通过多智能体对抗辩论机制缓解医疗多模态大语言模型的诊断幻觉问题，提升推理可信度和解释忠实度。
摘要：
医疗多模态大语言模型（MLLMs）在医疗领域面临严重的确认偏见问题，常通过幻觉视觉细节支持初始可能错误的诊断假设。现有链式推理（CoT）方法缺乏内在纠正机制，易导致误差传播。为此，我们提出Dialectic-Med，一种多智能体框架，通过对抗性辩证过程强化诊断严谨性。不同于静态共识模型，Dialectic-Med orchestrate动态交互三个角色专业化智能体：提出者制定诊断假设；对手配备新型视觉否证模块，主动检索矛盾视觉证据挑战提出者；调解者通过加权共识图解决冲突。通过显式建模否证认知过程，我们的框架确保诊断推理紧密基于验证的视觉区域。在MIMIC-CXR-VQA、VQA-RAD和PathVQA上的实证评估表明，Dialectic-Med不仅实现了最先进的性能，还从根本上提升了推理过程的可信度。除了准确性，我们的方法显著增强了解释忠实度，并果断缓解了幻觉，建立了超过单智能体基线的新标准。
英文摘要：
Multimodal Large Language Models (MLLMs) in healthcare suffer from severe confirmation bias, often hallucinating visual details to support initial, potentially erroneous diagnostic hypotheses. Existing Chain-of-Thought (CoT) approaches lack intrinsic correction mechanisms, rendering them vulnerable to error propagation. To bridge this gap, we propose Dialectic-Med, a multi-agent framework that enforces diagnostic rigor through adversarial dialectics. Unlike static consensus models, Dialectic-Med orchestrates a dynamic interplay between three role-specialized agents: a proponent that formulates diagnostic hypotheses; an opponent equipped with a novel visual falsification module that actively retrieves contradictory visual evidence to challenge the Proponent; and a mediator that resolves conflicts via a weighted consensus graph. By explicitly modeling the cognitive process of falsification, our framework guarantees that diagnostic reasoning is tightly grounded in verified visual regions. Empirical evaluations on MIMIC-CXR-VQA, VQA-RAD, and PathVQA demonstrate that Dialectic-Med not only achieves state-of-the-art performance but also fundamentally enhances the trustworthiness of the reasoning process. Beyond accuracy, our approach significantly enhances explanation faithfulness and decisively mitigates hallucinations, establishing a new standard over single-agent baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
