@inproceedings{zhang-etal-2026-preference-learning,
    title = "Preference Learning Unlocks {LLM}s' Psycho-Counseling Skills",
    author = "Zhang, Mian  and
      Eack, Shaun M.  and
      Chen, Zhiyu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.521/",
    pages = "10729--10750",
    ISBN = "979-8-89176-395-1",
    abstract = "Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle to consistently provide effective responses to client speeches, largely due to the lack of supervision from high-quality real psycho-counseling data, whose content is typically inaccessible due to client privacy concerns. Furthermore, the quality of therapists' responses in available sessions can vary significantly based on their professional training and experience. Assessing the quality of therapists' responses remains an open challenge. We address these challenges by first proposing a set of professional and comprehensive principles to evaluate therapists' responses to client speeches. Using these principles, we create a **Psy**cho-**Co**unseling **Pref**erence dataset, **PsyCoPref**, which contains 36k high-quality preference comparison pairs. This dataset aligns with the preferences of professional psychotherapists, providing a robust foundation for evaluating and improving LLMs in psycho-counseling. Experiments on reward modeling and preference learning demonstrate that PsyCoPref is an excellent resource for LLMs to acquire essential skills for responding to clients in a counseling session. Our best-aligned model achieves an impressive win rate of 87{\%} against GPT-4o."
}