Beyond Compliance: A Resistance-Informed Motivation Reasoning Framework for Challenging Psychological Client Simulation

TL;DR

ResistClient is a novel framework that models challenging client behaviors in psychological simulators, improving realism and reasoning coherence for training and evaluating mental health dialogue systems.

Contribution

It introduces Resistance-Informed Motivation Reasoning (RIMR), a two-stage training method that enhances simulator challenge fidelity and behavioral plausibility.

Findings

ResistClient outperforms existing simulators in challenge fidelity and reasoning coherence.

RIMR effectively mitigates compliance bias in psychological conversation models.

The framework facilitates better evaluation of psychological LLMs under challenging conditions.

Abstract

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.