构建中文心理支持对话数据集并设计多智能体系统提升真实对话质量
Toward Real-World Chinese Psychological Support Dialogues: CPsDD Dataset and a Co-Evolving Multi-Agent System
- 用预设路径生成对话，再通过专家知识优化质量
- 建成包含68000条对话的CPsDD数据集，覆盖16种心理问题
- 多智能体系统可精准识别用户特征并生成共情回应
随着心理压力增大，心理支持需求上升，但非英语语言相关数据集仍严重不足。为此，我们提出一个框架，利用有限真实数据与专家知识微调两个大模型：对话生成器和对话修正器。生成器基于预设路径生成大规模心理辅导对话，指导响应策略与用户互动；修正器则使对话更贴近真实数据质量。经自动与人工审核，构建了中文心理支持对话数据集（CPsDD），包含68,000条对话，覆盖13类群体、16种心理问题、13种成因及12个支持重点。此外，提出综合智能体对话支持系统（CADSS），包含用户画像分析器、历史摘要器、策略规划器和共情回应生成器。在策略预测与情感支持对话任务中，CADSS在CPsDD与ESConv数据集上均达到领先性能。
原文摘要 · Abstract (English)
The growing need for psychological support due to increasing pressures has exposed the scarcity of relevant datasets, particularly in non-English languages. To address this, we propose a framework that leverages limited real-world data and expert knowledge to fine-tune two large language models: Dialog Generator and Dialog Modifier. The Generator creates large-scale psychological counseling dialogues based on predefined paths, which guide system response strategies and user interactions, forming the basis for effective support. The Modifier refines these dialogues to align with real-world data quality. Through both automated and manual review, we construct the Chinese Psychological support Dialogue Dataset (CPsDD), containing 68K dialogues across 13 groups, 16 psychological problems, 13 causes, and 12 support focuses. Additionally, we introduce the Comprehensive Agent Dialogue Support System (CADSS), where a Profiler analyzes user characteristics, a Summarizer condenses dialogue history, a Planner selects strategies, and a Supporter generates empathetic responses. The experimental results of the Strategy Prediction and Emotional Support Conversation (ESC) tasks demonstrate that CADSS achieves state-of-the-art performance on both CPsDD and ESConv datasets.
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。