当来访者不再跟随：基于认知概念化图的策略性咨询框架
When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling
AI总结：
针对现有评估协议中来访者过度顺从导致评分虚高的问题，提出基于认知行为疗法的抵抗感知框架，通过认知概念化图模拟动态抵抗，并利用强化学习优化策略推理与响应生成，以提升在困难咨询交互中的策略鲁棒性。
摘要：
大型语言模型（LLMs）在心理咨询中展现出潜力，但现有基准高度依赖高度合作的模拟来访者。我们观察到一个关键的咨询师-来访者跟随现象：这些来访者往往在仅几轮对话后便迅速从抵抗转向顺从，造成治疗进展的假象，并通过表面共情在当前评估协议下虚高分数。为解决这一评估失配问题，我们提出一个基于认知行为疗法（CBT）的抵抗感知框架。我们引入CARS，一个通过认知概念化图（CCDs）显式建模动态抵抗的来访者模拟器。我们提出STREAMS，一个将策略推理（思考者）与响应生成（呈现者）解耦并通过强化学习优化的双模块框架。我们进一步提出EWTS-MI，一个用于评估高摩擦交互下响应性的熵加权指标。在抵抗性和非抵抗性咨询设置上的实验验证了我们对评估失配的发现，并展示了抵抗感知训练在挑战性咨询交互下提升策略鲁棒性的有效性。
英文摘要：
Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We observe a critical counselor-following phenomenon: these clients often rapidly shift from resistance to compliance after only a few turns, creating an illusion of therapeutic progress and inflating scores under current evaluation protocols through superficial empathy. To address this evaluation mismatch, we propose a Cognitive Behavioral Therapy (CBT)-grounded resistance-aware framework. We introduce CARS, a client simulator that explicitly models dynamic resistance via Cognitive Conceptualization Diagrams (CCDs). We present STREAMS, a dual-module framework that decouples strategic reasoning (Thinker) from response generation (Presenter) and optimizes it via reinforcement learning. We further propose EWTS-MI, an entropy-weighted metric for evaluating responsiveness under high-friction interactions. Experiments across resistant and non-resistant counseling settings validate our findings on evaluation mismatch and demonstrate the effectiveness of resistance-aware training for improving strategic robustness under challenging counseling interactions.
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。
