Beyond Compliance: A Resistance-Informed Motivation Reasoning Framework for Challenging Psychological Client Simulation
For developers of psychological training simulators and mental health dialogue systems, this work addresses the critical bottleneck of over-compliance in client simulation, enabling more realistic training and evaluation.
Existing psychological client simulators are unrealistically compliant, failing to prepare counselors for real-world challenging behaviors. The authors propose ResistClient, which models challenging client behaviors using a resistance-informed motivation reasoning framework, and show it significantly outperforms existing simulators in challenge fidelity, behavioral plausibility, and reasoning coherence.
Psychological client simulators have emerged as a scalable solution for training and evaluating counselor trainees and psychological LLMs. Yet existing simulators exhibit unrealistic over-compliance, leaving counselors underprepared for the challenging behaviors common in real-world practice. To bridge this gap, we present ResistClient, which systematically models challenging client behaviors grounded in Client Resistance Theory by integrating external behaviors with underlying motivational mechanisms. To this end, we propose Resistance-Informed Motivation Reasoning (RIMR), a two-stage training framework. First, RIMR mitigates compliance bias via supervised fine-tuning on RPC, a large-scale resistance-oriented psychological conversation dataset covering diverse client profiles. Second, beyond surface-level response imitation, RIMR models psychologically coherent motivation reasoning before response generation, jointly optimizing motivation authenticity and response consistency via process-supervised reinforcement learning. Extensive automatic and expert evaluations show that ResistClient substantially outperforms existing simulators in challenge fidelity, behavioral plausibility, and reasoning coherence. Moreover, ResistClient facilities evaluation of psychological LLMs under challenging conditions, offering new optimization directions for mental health dialogue systems.