ChatCLIDS: 模拟说服性人工智能对话以促进1型糖尿病护理中的闭环胰岛素采用
ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care
AI总结：
本文提出ChatCLIDS基准，用于评估基于LLM的说服对话在健康行为改变中的效果，通过模拟多轮交互和长期咨询场景，揭示当前LLM在行为改变中的局限性。
摘要：
1型糖尿病患者闭环胰岛素输注系统（CLIDS）的现实世界采用率仍较低，原因并非技术失败，而是多样的行为、心理社会和社会障碍。我们引入ChatCLIDS，首个严格评估LLM驱动说服对话用于健康行为改变的基准。我们的框架包含专家验证的虚拟患者库，每个患者具有临床扎根、异质的特征和现实的采用障碍，并模拟与配备多种证据支持说服策略的护士代理的多轮交互。ChatCLIDS独特支持长期咨询和对抗性社会影响场景，实现稳健、多维评估。我们的发现表明，尽管较大且更反思的LLM能随时间调整策略，但所有模型在克服阻力方面均面临困难，尤其是在现实中的社会压力下。这些结果突显了当前LLM在行为改变中的关键限制，并提供了一个高保真、可扩展的测试平台，以推动可信说服AI在医疗及其他领域的发展。
英文摘要：
Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse behavioral, psychosocial, and social barriers. We introduce ChatCLIDS, the first benchmark to rigorously evaluate LLM-driven persuasive dialogue for health behavior change. Our framework features a library of expert-validated virtual patients, each with clinically grounded, heterogeneous profiles and realistic adoption barriers, and simulates multi-turn interactions with nurse agents equipped with a diverse set of evidence-based persuasive strategies. ChatCLIDS uniquely supports longitudinal counseling and adversarial social influence scenarios, enabling robust, multi-dimensional evaluation. Our findings reveal that while larger and more reflective LLMs adapt strategies over time, all models struggle to overcome resistance, especially under realistic social pressure. These results highlight critical limitations of current LLMs for behavior change, and offer a high-fidelity, scalable testbed for advancing trustworthy persuasive AI in healthcare and beyond.
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。
