arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.04448cs.AI
收藏

PSY-STEP:结构化治疗目标和行动序列用于前瞻性咨询对话系统

PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems

Graduate School of Artificial Intelligence, POSTECH(浦项工业大学人工智能研究生院);Department of Computer Science and Engineering, POSTECH(浦项工业大学计算机科学与工程系);MILA;McGill University(麦吉尔大学)

Jihyun Lee, Yejin Min, Yejin Jeon, SungJun Yang, Hyounghun Kim, Gary Geunbae Lee

AI总结:

本文提出PSY-STEP框架,通过结构化治疗目标和行动序列提升咨询对话系统的主动性和有效性,实验表明其在临床相关性、连贯性和个性化方面优于现有模型。

摘要:

认知行为疗法(CBT)旨在识别和重构与事件无关的自动负面思维,但现有咨询代理在对话环境中难以识别和解决这些问题。为此,我们引入STEP数据集,通过显式反映自动思维和动态行动序列来建模CBT咨询。利用该数据集,我们训练了STEPPER咨询代理,能够主动引发自动思维并执行基于认知的干预。为进一步提高决策准确性和同理心响应,我们通过基于模拟合成咨询会话的偏好学习优化STEPPER。广泛对齐CBT的评估表明,与现有强基线模型相比,STEPPER提供了更临床相关、连贯和个性化的咨询,并在不引起情绪紊乱的情况下实现了更高的咨询师能力。

英文摘要:

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.

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。

↑