@inproceedings{yang-etal-2025-consistent,
    title = "Consistent Client Simulation for Motivational Interviewing-based Counseling",
    author = "Yang, Yizhe  and
      Achananuparp, Palakorn  and
      Huang, Heyan  and
      Jiang, Jing  and
      Lim, Nicholas Gabriel  and
      Ern, Cameron Tan Shi  and
      Kit, Phey Ling  and
      Xiuhui, Jenny Giam  and
      Pinto, John  and
      Lim, Ee-Peng",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1021/",
    pages = "20959--20998",
    ISBN = "979-8-89176-251-0",
    abstract = "Simulating human clients in mental health counseling is crucial for training and evaluating counselors (both human or simulated) in a scalable manner. Nevertheless, past research on client simulation did not focus on complex conversation tasks such as mental health counseling. In these tasks, the challenge is to ensure that the client{'}s actions (i.e., interactions with the counselor) are consistent with with its stipulated profiles and negative behavior settings. In this paper, we propose a novel framework that supports consistent client simulation for mental health counseling. Our framework tracks the mental state of a simulated client, controls its state transitions, and generates for each state behaviors consistent with the client{'}s motivation, beliefs, preferred plan to change, and receptivity. By varying the client profile and receptivity, we demonstrate that consistent simulated clients for different counseling scenarios can be effectively created. Both our automatic and expert evaluations on the generated counseling sessions also show that our client simulation method achieves higher consistency than previous methods."
}