When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling

2026-06-02

AI Summary

This study addresses the overestimation of large language models’ (LLMs) performance in counseling assessment, which stems from reliance on highly cooperative simulated clients and neglect of client resistance commonly encountered in real-world settings. To bridge this gap, the authors propose STREAMS, a dual-module framework comprising a strategy-reasoning Thinker and a response-generating Presenter, which integrates cognitive conceptualization diagrams (CCDs) into LLM-based counseling for the first time to dynamically model resistance behaviors. The framework further leverages reinforcement learning to optimize counseling strategies. Additionally, the work introduces CARS, a resistant-client simulator, and EWTS-MI, an entropy-weighted evaluation metric, to more realistically assess response quality under high-friction interactions. Experimental results demonstrate that resistance-aware training significantly enhances the model’s strategic robustness and response effectiveness in challenging counseling scenarios.

Abstract

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.

Problem

• evaluation mismatch
• resistance
• simulated clients
• therapeutic progress
• counseling benchmarks

Innovation

• resistance-aware counseling
• Cognitive Conceptualization Diagrams
• reinforcement learning
• client simulation
• entropy-weighted metric