arXiv cs.CL· Huachuan Qiu, Zhaoming Chen, Yuqian Chen, Yuan Xie, Yu Lu, Zhenzhong Lan·· 13 小时前AI 评分31
PsyCLIENT：用对话轨迹建模模拟心理咨询来访者，用于培训与模型评估
PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counseling
AI 导读
PsyCLIENT 框架通过来访者画像、对话历史和对话轨迹来约束模拟来访者每一轮的回复行为与内容，并构建了覆盖 60 个咨询主题的 120 份中文来访者画像数据集 PsyCLIENT-CP。24 位专业咨询师评估显示，PsyCLIENT 在真实感和培训实用性上评分高于对比方法；在来源识别研究中，其生成的对话被误判为真人来访者交互的频率也高于基线。该工作已被 EMNLP 2026 主会接收。
正文 · 原文
Abstract:LLM-based client simulation provides a scalable approach to novice counselor training, counseling-dialogue synthesis, and interactive evaluation of automated counseling systems. However, existing approaches are limited by insufficient profile diversity, weak behavioral grounding, and the lack of open Chinese-language resources for simulated counseling clients. We propose PsyCLIENT, a framework that conditions simulated-client responses on client profiles, dialogue histories, and conversational trajectories specifying target behaviors and content constraints at each client turn. We also construct PsyCLIENT-CP, a dataset of 120 Chinese client profiles spanning 60 counseling topics. Evaluations involving 24 professional counselors show that PsyCLIENT receives higher ratings of perceived authenticity and training utility than the comparison methods. In a separate source-identification study, PsyCLIENT dialogues were more frequently misclassified as human-client interactions than those generated by the baselines. These results suggest that conversational trajectory modeling can transform static client profiles into behavior-guided, dynamically unfolding counseling interactions.
| Comments: | Accepted to EMNLP 2026 (Main Conference) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2601.07312 [cs.CL] |
| (or arXiv:2601.07312v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2601.07312 arXiv-issued DOI via DataCite |
Submission history
From: Huachuan Qiu [view email]
[v1]
Mon, 12 Jan 2026 08:33:05 UTC (1,840 KB)
[v2]
Mon, 7 Sep 2026 06:57:46 UTC (1,842 KB)
[v3]
Thu, 22 Oct 2026 08:43:07 UTC (1,842 KB)
来源：arXiv cs.CL · arxiv.org