arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.15787cs.CLcs.IR
收藏

交互式智能体:通过角色扮演的LLM-LLM交互模拟咨询师-来访者心理咨询

Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions

School of Engineering, Westlake University(西lake大学工程学院)

Huachuan Qiu, Zhenzhong Lan

AI总结:

提出Interactive Agents框架,通过LLM-LLM角色扮演生成高质量心理咨询对话数据,解决隐私、成本和扩展性问题,并验证其治疗有效性和模型性能。

摘要:

创建有效的心理健康支持对话系统需要高质量的多轮咨询对话数据,然而收集真实的咨询师-来访者对话面临重大挑战,包括隐私问题、高成本和有限的扩展性。我们提出了 extbf{Interactive Agents},一个新颖的框架,通过受控的LLM-LLM交互模拟自然的咨询对话。该框架引入了两个关键创新:(1) 一个个性化的来访者智能体,在整个会话过程中保持一致的心理学特征;(2) 一个咨询师智能体,实现了一个基于理论的三阶段治疗模型,包括探索、洞察和行动阶段。通过使用自动评估指标和基于工作联盟清单的专业咨询师评估进行严格评估,我们证明我们的框架生成了具有治疗有效性的对话,其质量与人类生成的会话相当。在我们的合成数据集(SimPsyDial)上微调的模型,在基于LLM的咨询师的标准成对聊天机器人竞技场评估中达到了最先进的性能。我们的框架提供了一种可扩展、保护隐私的方法,用于生成高质量的咨询对话数据,同时保持专业的治疗标准。

英文摘要:

Creating effective dialogue systems for mental health support requires high-quality multi-turn counseling dialogue data, yet collecting real counselor-client conversations presents significant challenges, including privacy concerns, high costs, and limited scalability. We present \textbf{Interactive Agents}, a novel framework that simulates naturalistic counseling dialogues through controlled LLM-to-LLM interactions. The framework introduces two key innovations: (1) a personalized client agent that maintains consistent psychological characteristics throughout a session, and (2) a counselor agent that implements a theoretically grounded three-stage therapeutic model comprising the exploration, insight, and action phases. Through rigorous evaluation using both automatic metrics and professional-counselor assessments based on the Working Alliance Inventory, we demonstrate that our framework generates therapeutically valid dialogues that are comparable in quality to human-generated sessions. Models fine-tuned on our proposed synthetic dataset (SimPsyDial) achieve state-of-the-art performance in a standard pairwise chatbot-arena evaluation of LLM-based counselors. Our framework provides a scalable, privacy-preserving method for generating high-quality counseling dialogue data while maintaining professional therapeutic standards.

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。

↑