PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling

2026-01-12

AI Summary

Current large language models (LLMs) face significant limitations in counseling simulation, including insufficient response diversity, constrained realism, and inadequate support for Chinese-language contexts, thereby hindering their utility in therapist training and system evaluation. To address these challenges, this work proposes a client simulation framework grounded in conversational trajectory modeling, which guides LLMs to generate dialogues that are highly consistent, diverse, and realistic through predefined behavioral trajectories. The study introduces a controllable generation approach that integrates explicit behavioral labels with content constraints and releases PsyCLIENT-CP—the first open-source Chinese client persona dataset, encompassing 60 distinct counseling topics. Expert evaluations demonstrate that the simulated clients achieve a 95% confusion rate in perceived authenticity, substantially outperforming existing baseline methods.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

LLM-based client simulation has emerged as a promising tool for training novice counselors and evaluating automated counseling systems. However, existing client simulation approaches face three key challenges: (1) limited diversity and realism in client profiles, (2) the lack of a principled framework for modeling realistic client behaviors, and (3) a scarcity in Chinese-language settings. To address these limitations, we propose PsyCLIENT, a novel simulation framework grounded in conversational trajectory modeling. By conditioning LLM generation on predefined real-world trajectories that incorporate explicit behavior labels and content constraints, our approach ensures diverse and realistic interactions. We further introduce PsyCLIENT-CP, the first open-source Chinese client profile dataset, covering 60 distinct counseling topics. Comprehensive evaluations involving licensed professional counselors demonstrate that PsyCLIENT significantly outperforms baselines in terms of authenticity and training effectiveness. Notably, the simulated clients are nearly indistinguishable from human clients, achieving an about 95\% expert confusion rate in discrimination tasks. These findings indicate that conversational trajectory modeling effectively bridges the gap between theoretical client profiles and dynamic, realistic simulations, offering a robust solution for mental health education and research. Code and data will be released to facilitate future research in mental health counseling.

Problem

• client simulation
• mental health counseling
• conversational trajectory
• LLM-based simulation
• Chinese-language setting

Innovation

• conversational trajectory modeling
• LLM-based client simulation
• mental health counseling
• Chinese client profile dataset
• behavior-constrained generation