让对话机器人主动识别并干预负面思维，提升心理咨询效果。
PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems
- 构建包含自动负向思维与干预步骤的对话数据集
- 训练出能主动引导和认知干预的智能咨询代理
- 结合情感共情优化，效果优于现有模型
认知行为疗法（CBT）旨在识别并重构对事件的自动化负性思维，但现有咨询对话系统难以在对话中有效识别与应对。为此，我们提出STEP数据集，通过显式标注自动化思维及动态干预步骤来建模CBT咨询过程。基于此数据集，我们训练了STEPPER——一个能主动引导用户暴露自动化思维并执行认知基础干预的咨询代理。为进一步提升决策准确性和情感共情能力，我们采用模拟合成会话进行偏好学习微调。大量基于CBT准则的评估表明，STEPPER在临床合理性、连贯性和个性化方面优于多个强基线模型，且在不引发情绪不适的前提下实现了更高咨询胜任力。
原文摘要 · Abstract (English)
Cognitive Behavioral Therapy (CBT) aims to identify and restructure automatic negative thoughts pertaining to involuntary interpretations of events, yet existing counseling agents struggle to identify and address them in dialogue settings. To bridge this gap, we introduce STEP, a dataset that models CBT counseling by explicitly reflecting automatic thoughts alongside dynamic, action-level counseling sequences. Using this dataset, we train STEPPER, a counseling agent that proactively elicits automatic thoughts and executes cognitively grounded interventions. To further enhance both decision accuracy and empathic responsiveness, we refine STEPPER through preference learning based on simulated, synthesized counseling sessions. Extensive CBT-aligned evaluations show that STEPPER delivers more clinically grounded, coherent, and personalized counseling compared to other strong baseline models, and achieves higher counselor competence without inducing emotional disruption.
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。