用大模型模拟失智患者日常行为，帮照护者练习应对策略。
An Interactive LLM-Based Simulator for Dementia-Related Activities of Daily Living
- 用大模型生成带严重程度和照护场景的多轮对话行为。
- 专家评分显示模拟行为中度到高度可信，平均每轮6次交互。
- 适合照护培训、智能助手开发与政策制定者使用。
有效失智照护需训练与灵活沟通，但现有助老AI与机器人受限于缺乏情境丰富且保护隐私的阿尔茨海默病及相关痴呆症（ADRD）患者日常生活活动（ADLs）行为数据。本文提出一个基于网页的大语言模型（gpt-5-mini）模拟器，可生成受痴呆严重程度与照护场景（及在场景中时长）调节的多轮患者行为，配以轻量级行为提示（括号内）。用户设定病情严重度、照护场景与具体ADL任务；每轮患者发言后，用户评分真实度（1–5），可附评论，并以自由输入或选择/修改四个策略建议（识别、协商、引导、共情）作回应。开展在线专家参与式预研测试（14位失智照护专家，18场次，112轮评分）。模拟行为获评中等到高度可信，典型会话长度为六轮。专家对54.5%的回合自行撰写回复；‘识别’与‘引导’策略最常被选用。对评论进行主题分析，提炼出六类失败模式，揭示在日常活动锚定与照护场景一致性方面的常见问题，指导提示词与工作流优化。模拟器与交互日志支持证据驱动的协同模拟迭代，助力照护数据收集、培训系统与辅助智能体/机器人策略开发。
原文摘要 · Abstract (English)
Effective dementia caregiving requires training and adaptive communication, but assistive AI and robotics are constrained by a lack of context-rich, privacy-sensitive data on how people living with Alzheimer's disease and related dementias (ADRD) behave during activities of daily living (ADLs). We introduce a web-based simulator that uses a large language model (gpt-5-mini) to generate multi-turn, severity- and care-setting-conditioned patient behaviors during ADL assistance, pairing utterances with lightweight behavioral cues (in parentheses). Users set dementia severity, care setting (and time in setting), and ADL; after each patient turn they rate realism (1-5) with optional critique, then respond as the caregiver via free text or by selecting/editing one of four strategy-scaffolded suggestions (Recognition, Negotiation, Facilitation, Validation). We ran an online formative expert-in-the-loop study (14 dementia-care experts, 18 sessions, 112 rated turns). Simulated behavior was judged moderately to highly plausible, with a typical session length of six turns. Experts wrote custom replies for 54.5 percent of turns; Recognition and Facilitation were the most-used suggested strategies. Thematic analysis of critiques produced a six-category failure-mode taxonomy, revealing recurring breakdowns in ADL grounding and care-setting consistency and guiding prompt/workflow refinements. The simulator and logged interactions enable an evidence-driven refinement loop toward validated patient-caregiver co-simulation and support data collection, caregiver training, and assistive AI and robot policy development.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。