利用先进患者模拟器探索问询与诊断之间的关系
Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators
AI总结：
本文从真实医患对话中提取策略训练患者模拟器，以更高拟人化和更低幻觉率评估诊断模型，并通过实验揭示问询与诊断遵循李比希定律，同时提出四类问询类型以解释模型表现差异。
摘要：
近年来，大型语言模型展现出变革在线医疗咨询的巨大潜力。尽管如此，大多数研究致力于在信息充足的条件下提高诊断准确性，往往忽视了问询阶段。一些研究尝试通过使用提示工程构建的患者智能体来评估或优化医生模型。然而，仅靠提示工程难以准确模拟真实患者。我们需要探索患者模拟的新范式。此外，问询与诊断之间的关系仍未得到研究。本文从真实医患对话中提取对话策略，以指导患者模拟器的训练。我们的模拟器采用动态对话策略，表现出更高的拟人化和更低的幻觉率。这一创新为诊断模型提供了更准确的评估，并生成了逼真的合成数据。我们对问询与诊断之间的关系进行了大量实验，结果表明它们遵循李比希定律：无论诊断技能如何，问询不足都会限制诊断效果，反之亦然。实验还揭示了各模型在问询表现上的显著差异。为深入探究这一现象，问询过程被划分为四种不同类型。分析问询在这些类型中的分布有助于解释性能差异。我们的患者模拟器权重可在 https://github.com/PatientSimulator/PatientSimulator 获取。
英文摘要：
Recently, large language models have shown great potential to transform online medical consultation. Despite this, most research targets improving diagnostic accuracy with ample information, often overlooking the inquiry phase. Some studies try to evaluate or refine doctor models by using prompt-engineered patient agents. However, prompt engineering alone falls short in accurately simulating real patients. We need to explore new paradigms for patient simulation. Furthermore, the relationship between inquiry and diagnosis remains unexplored. This paper extracts dialogue strategies from real doctor-patient conversations to guide the training of a patient simulator. Our simulator shows higher anthropomorphism and lower hallucination rates, using dynamic dialogue strategies. This innovation offers a more accurate evaluation of diagnostic models and generates realistic synthetic data. We conduct extensive experiments on the relationship between inquiry and diagnosis, showing they adhere to Liebig's law: poor inquiry limits diagnosis effectiveness, regardless of diagnostic skill, and vice versa. The experiments also reveal substantial differences in inquiry performance among models. To delve into this phenomenon, the inquiry process is categorized into four distinct types. Analyzing the distribution of inquiries across these types helps explain the performance differences. The weights of our patient simulator are available https://github.com/PatientSimulator/PatientSimulator.
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。
