用多轮对话模拟真实心理咨询过程，提升模型长期陪伴能力。
Psychological Counseling Cannot Be Achieved Overnight: Automated Psychological Counseling Through Multi-Session Conversations
- 构建多轮心理辅导数据集，还原真实咨询进展轨迹。
- 模型在多轮对话中表现优于基线，能持续追踪用户状态。
- 适合长期心理服务、人机共情系统研究者参考。
近年来，大语言模型在自动化心理辅导方面取得显著进展。然而，现有研究主要聚焦于单轮对话，无法反映真实咨询场景。实际上，心理辅导是一个持续过程，需通过多轮互动逐步解决来访者问题。为克服这一局限，我们构建了多轮心理辅导对话数据集（MusPsy-Dataset），该数据集基于公开的心理案例报告中的真实客户资料，涵盖同一客户在不同会话中的多轮动态交流。基于此数据集，我们提出了MusPsy-Model，旨在追踪客户进展并随时间调整辅导方向。实验表明，该模型在多轮会话中均优于基线模型。
原文摘要 · Abstract (English)
In recent years, Large Language Models (LLMs) have made significant progress in automated psychological counseling. However, current research focuses on single-session counseling, which doesn't represent real-world scenarios. In practice, psychological counseling is a process, not a one-time event, requiring sustained, multi-session engagement to progressively address clients' issues. To overcome this limitation, we introduce a dataset for Multi-Session Psychological Counseling Conversation Dataset (MusPsy-Dataset). Our MusPsy-Dataset is constructed using real client profiles from publicly available psychological case reports. It captures the dynamic arc of counseling, encompassing multiple progressive counseling conversations from the same client across different sessions. Leveraging our dataset, we also developed our MusPsy-Model, which aims to track client progress and adapt its counseling direction over time. Experiments show that our model performs better than baseline models across multiple sessions.
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。