COCOA：采用认知扭曲专用记忆与动态提示的基于 CBT 的对话咨询智能体
COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt
AI总结：
本文提出 CoCoA 心理咨询智能体，通过认知扭曲专用记忆系统与动态提示灵活运用 CBT，并基于 Character.ai 对话数据集由 GPT 评估，证明其相较其他模型具有统计显著优势。
摘要：
提供心理健康护理的对话智能体需求正在持续增长。在本研究中，我们开发了一个名为 CoCoA 的心理咨询智能体，它运用认知行为疗法（CBT）技术来识别并处理来访者陈述中固有的认知扭曲。具体而言，我们构建了一个记忆系统，以高效管理咨询所需的信息，同时从来访者的话语中提取关于其的高层次洞察。此外，为确保咨询智能体生成恰当的回应，我们引入动态提示，以灵活运用 CBT 技术并促进对信息的适当检索。我们让 CoCoA 与来自 Character.ai 的角色进行对话，创建了一个用于评估的数据集。随后，我们请 GPT 对所构建的咨询数据集进行评估，结果显示我们的模型与其他模型之间存在具有统计显著性的差异。
英文摘要：
The demand for conversational agents that provide mental health care is consistently increasing. In this work, we develop a psychological counseling agent, referred to as CoCoA, that applies Cognitive Behavioral Therapy (CBT) techniques to identify and address cognitive distortions inherent in the client's statements. Specifically, we construct a memory system to efficiently manage information necessary for counseling while extracting high-level insights about the client from their utterances. Additionally, to ensure that the counseling agent generates appropriate responses, we introduce dynamic prompting to flexibly apply CBT techniques and facilitate the appropriate retrieval of information. We conducted dialogues between CoCoA and characters from Character.ai, creating a dataset for evaluation. Then, we asked GPT to evaluate the constructed counseling dataset, and our model demonstrated a statistically significant difference from other models.
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。
