Leveraging large language models to identify microcounseling skills in psychotherapy transcripts.

Objective: Microcounseling skills are fundamental to effective psychotherapy, yet manual coding is time- and resource-intensive. This study explores the potential of large language models (LLMs) to automate the identification of these skills in therapy sessions. Method: We fine-tuned GPT-4.1 on a se...

Descripción completa

Detalles Bibliográficos
Publicado en:Psychotherapy Research Vol. 36; no. 6; pp. 1058 - 1077
Autores principales: Hammerfald, Karin, Schmidt, Fabian, Vlassov, Vladimir, Haaland Jahren, Henrik, Solbakken, Ole André
Formato: Artículo
Publicado: Taylor & Francis Ltd Jul2026
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=194804733&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 194804733
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        10503307
        10T
      jtl: Psychotherapy Research
      issn: 10503307
      maglogo: N
    pubinfo:
      dt: Jul2026
      vid: 36
      iid: 6
      pid: 377
      pub: Taylor & Francis Ltd
    artinfo:
      ui:
        194804733
        10.1080/10503307.2025.2539405
      ppf: 1058
      ppct: 19
      formats:
      tig:
        atl: Leveraging large language models to identify microcounseling skills in psychotherapy transcripts.
      aug:
        au:
          Hammerfald, Karin
          Schmidt, Fabian
          Vlassov, Vladimir
          Haaland Jahren, Henrik
          Solbakken, Ole André
        affil:
          Department of Psychology, University of Oslo, Oslo, Norway
          Department of Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden
          Braive AS, Oslo, Norway
      su:
        Psychotherapy
        Counseling
        Generative pre-trained transformers
        Natural language processing
        Automatic classification
        Language models
        Machine learning
      sug:
        subj:
          Psychotherapy
          Counseling
          Other Individual and Family Services
          Generative pre-trained transformers
          Natural language processing
          Automatic classification
          Language models
          Machine learning
      keyword:
        artificial intelligence
        counseling skills
        large language models
        machine learning
        natural language processing
        artificial intelligence
        counseling skills
        large language models
        machine learning
        natural language processing
      ab: Objective: Microcounseling skills are fundamental to effective psychotherapy, yet manual coding is time- and resource-intensive. This study explores the potential of large language models (LLMs) to automate the identification of these skills in therapy sessions. Method: We fine-tuned GPT-4.1 on a set of psychotherapy transcripts annotated by human coders. The model was trained to classify therapist utterances, generate explanations for its decisions, and propose alternative responses. The pipeline included transcript preprocessing, dialogue segmentation, and supervised fine-tuning. Results: The model achieved solid performance (Accuracy: 0.78; Precision: 0.79; Recall: 0.78; F1: 0.78; Specificity: 0.77; Cohen's κ: 0.69). It reliably detected common and structurally distinct skills but struggled with more nuanced skills that rely on understanding implicit relational dynamics. Conclusion: Despite limitations, fine-tuned LLMs have potential for enhancing psychotherapy research and clinical practice by providing scalable, automated coding of therapist skills.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N