面向沟通式医疗辅导的大型语言模型基准评测：一种新型系统与数据集
Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset
AI总结：
本文提出ChatCoach人机协作框架及GCoT方法，通过患者智能体和教练智能体帮助医学学习者练习沟通技能，并构建评测数据集验证LLMs在沟通式医疗辅导任务上的有效性。
摘要：
自然语言处理（NLP）在医疗领域的传统应用主要集中于以患者为中心的服务，例如通过医疗对话系统增强患者交互和护理交付。然而，NLP在帮助经验不足的医生方面的潜力，尤其是在沟通式医疗辅导等领域，仍然基本未被探索。我们提出了“ChatCoach”，这是一个人类与AI协作框架，旨在帮助医学学习者在患者咨询过程中练习沟通技能。ChatCoach（我们的数据和代码可在线获取：https://github.com/zerowst/Chatcoach）与传统对话系统的不同之处在于，它提供了一个模拟环境，医学学习者可以在其中与患者智能体练习对话，同时由教练智能体提供即时、结构化的反馈。这一过程通过我们提出的广义思维链（Generalized Chain-of-Thought, GCoT）方法实现，该方法促进了结构化反馈的生成，并增强了对外部知识源的利用。此外，我们还专门开发了一个数据集，用于在ChatCoach框架内评估大型语言模型（LLMs）在沟通式医疗辅导任务上的表现。我们的实证结果验证了ChatCoach的有效性。
英文摘要：
Traditional applications of natural language processing (NLP) in healthcare have predominantly focused on patient-centered services, enhancing patient interactions and care delivery, such as through medical dialogue systems. However, the potential of NLP to benefit inexperienced doctors, particularly in areas such as communicative medical coaching, remains largely unexplored. We introduce "ChatCoach", a human-AI cooperative framework designed to assist medical learners in practicing their communication skills during patient consultations. ChatCoach (Our data and code are available online: https://github.com/zerowst/Chatcoach)differentiates itself from conventional dialogue systems by offering a simulated environment where medical learners can practice dialogues with a patient agent, while a coach agent provides immediate, structured feedback. This is facilitated by our proposed Generalized Chain-of-Thought (GCoT) approach, which fosters the generation of structured feedback and enhances the utilization of external knowledge sources. Additionally, we have developed a dataset specifically for evaluating Large Language Models (LLMs) within the ChatCoach framework on communicative medical coaching tasks. Our empirical results validate the effectiveness of ChatCoach.
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。
