arXiv 2604.163432026-03-16cs.HCcs.AI

Elder-Sim：一种经过心理测量学验证的用于构建性格稳定的老年人数字孪生平台

Elder-Sim: A Psychometrically Validated Platform for Personality-Stable Elderly Digital Twins

Yulin AI-Enhanced HealthCare Lab（云林人工智能增强医疗实验室）；School of Nursing, Fudan University（复旦大学护理学院）；School of Nursing, Medical College of Soochow University（苏州大学医学院护理学院）；School of Nursing, Dali University（大理大学护理学院）；Department of Advanced Interdisciplinary Studies, The University of Tokyo（东京大学先进跨学科研究部）；The First Affiliated Hospital of Soochow University（苏州大学第一附属医院）；Department of Nursing, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University（江西医学院护理部，南昌大学第一附属医院）；School of Social Development, East China University of Political Science and Law（中国政法大学社会发展学院）；Rory Meyers College of Nursing, New York University（纽约大学 Rory Meyers 护理学院）；New York University Shanghai（纽约大学上海校区）

Jiaqing Wang, Zhongfang Yang, Xingyuan Zhu, Zong'an Huang, Hao Wang, Li Tian, Ying Cao, Xiaomin Qu, Xiang Qi, Bei Wu, Zheng Zhu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出Elder-Sim平台，通过心理测量学验证方法构建性格稳定的老年人数字孪生代理，利用认知概念化图和LoRA微调提升性格一致性。

摘要：

背景：LLMs使面向患者的对话代理成为可能，为捕捉老年人的生活经历和行为反应提供了路径。核心障碍是性格漂移——在重复交互中特质表现不一致，这会削弱老年护理中生成轨迹和干预反应模拟的可靠性。目标：开发Elder-Sim，一种多角色的老年人护理对话平台，用于构建性格稳定的数字孪生代理，并提出心理测量学验证框架，以量化LLM代理的性格一致性。方法：Elder-Sim通过n8n工作流编排和本地LLM推理（Ollama/vLLM）实现，整合（1）大五（OCEAN）特质规范，（2）基于Beck CBT框架的认知概念化图（CCD），以及（3）基于MySQL的长期记忆模块。通过四个条件的消融研究——基线、+记忆、+CCD和+LoRA（在CHARLS的19717条指令对上微调）——评估Cronbach's α、ICC和角色区分准确率。结果：可靠性在各条件下均良好（Cronbach's α：0.70-0.94；ICC：0.85-0.96）。角色区分率从83.3%（基线）提升到88.9%（+记忆）、94.4%（+CCD）和97.2%（+LoRA）。CCD产生了最大的一致性提升（平均α 0.702→0.892），而LoRA实现了最高的整体一致性（α 0.940；ICC 0.958）。结论：Elder-Sim提供了一种经过心理测量学验证的方法，用于构建性格一致的老年人数字孪生代理。结构化认知建模和领域适应减少了性格漂移，支持老年人心理健康护理中的可靠纵向模拟，并在临床部署前支持可重复的计算机模拟评估。

英文摘要：

Background: LLMs enable patient-facing conversational agents, creating a pathway toward digital twins that capture older adults' lived experiences and behavioral responses across time. A central barrier is personality drift -- inconsistent trait expression across repeated interactions -- which undermines reliability of generated trajectories and intervention-response simulation in geriatric care. Objective: To develop ELDER-SIM, a multi-role elderly-care conversational platform for building personality-stable digital twin agents, and to propose a psychometric validation framework for quantifying personality consistency in LLM-based agents. Methods: ELDER-SIM was implemented via n8n workflow orchestration with local LLM inference (Ollama/vLLM), integrating (1) Big Five (OCEAN) trait specifications, (2) a Cognitive Conceptualization Diagram (CCD) grounded in Beck's CBT framework, and (3) a MySQL-based long-term memory module. Ablation studies across four conditions -- Baseline, +Memory, +CCD, and +LoRA (fine-tuned on 19,717 instruction pairs from CHARLS) -- were evaluated via Cronbach's $α$, ICC, and role discrimination accuracy. Results: Reliability was acceptable to excellent across conditions (Cronbach's $α$: 0.70--0.94; ICC: 0.85--0.96). Role discrimination improved from 83.3% (Baseline) to 88.9% (+Memory), 94.4% (+CCD), and 97.2% (+LoRA). CCD produced the largest consistency gain (mean $α$ 0.702$\to$0.892), while LoRA achieved the highest overall consistency ($α$ 0.940; ICC 0.958). Conclusions: ELDER-SIM provides a psychometrically validated approach for constructing personality-consistent elderly digital twin agents. Structured cognitive modeling and domain adaptation reduce personality drift, supporting reliable longitudinal simulation for elderly mental health care and reproducible in silico evaluation before clinical deployment.

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。