The paper examines how Large Language Models (LLMs) can act as simulated clients in online counselling training, comparing their performance to human role-players. Researchers recorded sessions where novice counsellors interacted with both human peers and LLM-generated clients (using Mistral’s Mixtral 8x7b with 4‑bit quantization), then analyzed the interactions at the sentence level using a counselling communication pattern system. Results show both similarities and differences in counselling patterns between the two scenarios, suggesting that LLM-based role‑plays can support competency development while also highlighting areas needing improvement in virtual client simulations.
By Eric Rudolph, Philipp Steigerwald, Jens Albrecht
PsyCLIENT is a framework that uses large language models to simulate counseling clients by conditioning responses on client profiles, dialogue histories, and conversational trajectories that specify target behaviors and content constraints. The authors created PsyCLIENT-CP, a dataset of 120 Chinese client profiles covering 60 counseling topics, and evaluated the system with 24 professional counselors, finding higher authenticity and training utility ratings compared to baseline methods. In a source-identification study, PsyCLIENT-generated dialogues were more often mistaken for real human-client interactions than those from other models, indicating the effectiveness of conversational trajectory modeling in producing realistic counseling conversations.
By Huachuan Qiu, Zhaoming Chen, Yuqian Chen, Yuan Xie, Yu Lu, Zhenzhong Lan
arXiv:2610.08250v1 Announce Type: new
Abstract: Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation r...
By Shixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang, Jingying Chen
The paper introduces StratCBT, a new dataset of 9,688 psychological counseling sessions with 256K utterances, each counselor response aligned to one of eight Cognitive Behavioral Therapy (CBT) strategies. It was created by modeling clients’ negative thoughts and generating high‑quality conversations through self‑chat, using realistic sessions for guidance. Experiments show that strategy‑aligned generation improves professional and effective counseling when evaluated with large language model‑simulated clients.
By Zimu Wang, Yiwen Jiang, Xiangyu Zhao, Yaling Shen, Jiahe Liu, Stephanie Fong, Maxmartwell H Cheng, Guilherme C Oliveira, Anh Nguyen, Robert Desimone, Barnaby Nelson, Dominic Dwyer, Zongyuan Ge
arXiv:2608. 07499v1 Announce Type: cross Abstract: The development and benchmarking of Large Language Model (LLM)-based Motivational Interviewing (MI) counsellors now often rely on LLM-based simulated clients.
By Jiading Zhu, Xinyu Cindy Wang, Thomas Nguyen, Yan Qing Lee, Osnat C. Melamed, Peter Selby, Jonathan Rose
arXiv:2409.02244v3 Announce Type: replace-cross
Abstract: Large language models (LLMs) are increasingly being used as ad hoc therapists. While prior research has found that LLMs outperform human coun...
By Zainab Iftikhar, Sean Ransom, Amy Xiao, Nicole Nugent, Jeff Huang
arXiv:2608.22251v1 Announce Type: cross
Abstract: Rising global demand for mental health support creates significant service delivery challenges, with asynchronous email counselling serving as a cruc...
By Philipp Steigerwald, Nico Bienlein, Jennifer Burghardt, Mara Stieler, Robert Lehmann, Jens Albrecht
arXiv:2606. 05793v1 Announce Type: cross Abstract: While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging.
By Hong Qian, Yuanhao Liu, Zihan Zhou, Zongbao Zhang, Hanjie Ge, Haotian Shi, Liang Dou, Xiangfeng Wang, Jingwen Yang, Aimin Zhou
The paper introduces a three-tier persona vector to generate diverse, realistic user inputs for evaluating tool-augmented LLM agents. The vector includes 23 dimensions: categorical demographics, continuous behavioral traits, and continuous emotional states, plus a query-complexity overlay. Experiments on 64,698 conversations show that these persona dimensions produce measurable differences in agent performance and realistic scenario-reactive behavior.
The paper introduces a three-tier persona vector for user simulation in evaluating LLM agents, comprising 23 dimensions across demographics, behavioral traits, and emotional states, plus a query-complexity overlay. It demonstrates that these nuanced personas generate diverse, scenario-reactive conversations, leading to significant variations in agent goal achievement and compliance across different contexts. The model’s design allows for reproducible, auditable user behavior patterns without relying on learned covariance matrices.
By Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu, Mayank Malhotra, Arup Kumar Das, Jitesh Chandra Mishra, Arun Menon, Avinash Karn, Mouli V
LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift.
arXiv:2608. 12750v1 Announce Type: cross Abstract: LLM-based simulated clients are increasingly used to train novice counselors, evaluate LLM therapists, and generate synthetic data.
By Sahand Sabour, TszYam NG, Yaqian Chen, Guanqun Bi, Jialu Zhao, Minlie Huang