When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling
Quick Take
The study introduces CARS, a client simulator utilizing Cognitive Conceptualization Diagrams, and STREAMS, a dual-module framework that separates strategic reasoning from response generation. It addresses evaluation mismatches in LLMs for psychological counseling by implementing resistance-aware training, validated through experiments demonstrating improved strategic robustness in challenging interactions.
Key Points
- CARS models dynamic resistance in clients using Cognitive Conceptualization Diagrams.
- STREAMS framework separates strategic reasoning (Thinker) from response generation (Presenter).
- Introduces EWTS-MI, an entropy-weighted metric for evaluating responsiveness.
- Experiments show improved strategic robustness in resistant counseling settings.
- Addresses the illusion of therapeutic progress in existing LLM evaluations.
Article Content
From source RSS / original summaryarXiv:2606. 04389v1 Announce Type: new 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.