构建稳定人格的老人数字孪生，用心理测量法验证AI行为一致性
Elder-Sim: A Psychometrically Validated Platform for Personality-Stable Elderly Digital Twins
- 用认知模型和长期记忆约束AI言行，防止性格随对话漂移
- 引入专业框架后，人格一致性指标提升至0.892（α值），最高达0.940
- 适合老年心理健康模拟、临床前测试，支持精准干预评估
背景：大模型使面向患者的对话代理成为可能，为构建捕捉老年人生活经验与行为反应的数字孪生提供了路径。主要障碍是人格漂移——重复交互中人格特征表达不一致，削弱了生成轨迹与干预响应模拟的可靠性。目标：开发ELDER-SIM，一个支持多角色的老年护理对话平台，用于构建人格稳定的数字孪生代理，并提出心理测量验证框架以量化大模型代理的人格一致性。方法：通过n8n工作流编排实现ELDER-SIM，采用本地大模型推理（Ollama/vLLM），集成三大模块：（1）五大性格特质（OCEAN）设定，（2）基于贝克认知行为疗法的认知概念图（CCD），（3）基于MySQL的长期记忆模块。在四种条件下进行消融实验：基础模型、+记忆、+CCD、+LoRA（在CHARLS的19,717条指令对上微调）。使用克朗巴赫α系数、组内相关系数（ICC）及角色判别准确率评估。结果：各条件下的可靠性达到可接受至优秀水平（克朗巴赫α：0.70–0.94；ICC：0.85–0.96）。角色判别准确率从基础模型的83.3%提升至+记忆的88.9%、+CCD的94.4%、+LoRA的97.2%。其中CCD带来最大一致性提升（平均α由0.702升至0.892），而LoRA实现最高整体一致性（α=0.940，ICC=0.958）。结论：ELDER-SIM提供了一种心理测量学验证的方法，可构建人格一致的老年人数字孪生代理。结构化认知建模与领域适配有效减少人格漂移，支持可靠的时间序列模拟，适用于老年心理健康照护与临床部署前的可复现虚拟评估。
原文摘要 · Abstract (English)
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.
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。