发表机构
The Chinese University of Hong Kong; The University of Hong Kong; Guangdong Provincial Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)（香港中文大学; 香港大学; 广东省人工智能与数字经济实验室（深圳））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对认知刺激疗法在低资源语言（如粤语）中的数据稀缺与共情-协议平衡难题，提出STaR-CS数据合成与RCA反思性对齐框架，显著提升协议遵循、安全性与群体引导效果。
AI 中文摘要
认知刺激疗法（CST）为认知障碍老年人提供非药物支持，但其可扩展性受限于对受过培训的引导者的依赖以及严重的数据稀缺，尤其是对于粤语等隐私敏感、低资源语言。尽管大语言模型（LLMs）在自动化陪伴方面展现出潜力，但它们往往难以在共情参与与遵循认知刺激指南之间取得平衡。我们提出一个框架，从两个互补的维度应对这些挑战。首先，STaR-CS（风格迁移与角色条件化认知刺激）通过引导者风格建模和结构化骨架提取来合成多方对话，缓解数据障碍。在此语料库基础上，反思性认知对齐（RCA）框架将刺激交互建模为顺序决策过程，整合协议约束的认知链（PC-CoC）以进行结构化推理，以及推理时价值对齐（IVA）以基于安全和参与目标进行原则性的响应选择。在六个骨干大语言模型和两位独立评估者的评估中，RCA在协议遵循、安全性和群体引导方面始终优于标准提示基线。我们的代码可在以下网址获取：此HTTPS URL。
英文摘要
Cognitive Stimulation Therapy (CST) offers non-pharmacological support for elders with cognitive impairment, yet scalability remains constrained by reliance on trained facilitators and severe data scarcity, particularly for privacy-sensitive, low-resource languages such as Cantonese. While Large Language Models (LLMs) show promise for automated companionship, they often struggle to balance empathetic engagement with adherence to cognitive stimulation guidelines. We propose a framework addressing these challenges along two complementary axes. First, STaR-CS (Style-Transfer and Role-Conditioned Cognitive Stimulation) synthesizes multi-party dialogues through facilitator style modeling and structured skeleton extraction, mitigating data barriers. Building upon this corpus, the Reflective Cognitive Alignment (RCA) framework models stimulation interactions as a sequential decision process, integrating Protocol-Constrained Chain-of-Cognition (PC-CoC) for structured reasoning and Inference-Time Value Alignment (IVA) for principled response selection based on safety and engagement goals. Evaluations across six backbone LLMs and two independent judges show that RCA consistently improves protocol adherence, safety, and group facilitation over standard prompting baselines. Our code is available at https://github.com/jiangjyjy/RCA_Agent.
