Zobraziť v EDS

AI meets psychology: an exploratory study of large language models’ competence in psychotherapy contexts

Uložené v:
Podrobná bibliografia
Názov: AI meets psychology: an exploratory study of large language models’ competence in psychotherapy contexts
Autori: Sian Tan, Kean, Cervin, Matti, Leman, Patrick, Nielsen, Kristopher, Vasantha Kumar, Prashanth, Medvedev, Oleg N.
Prispievatelia: Lund University, Faculty of Medicine, Department of Clinical Sciences, Lund, Section IV, Child and Adolescent Psychiatry, Innovations in pediatric mental health, Lunds universitet, Medicinska fakulteten, Institutionen för kliniska vetenskaper, Lund, Sektion IV, Barn- och ungdomspsykiatri, Innovations in pediatric mental health, Originator
Zdroj: Journal of Psychology and AI. 1(1):1-17
Predmety: Medical and Health Sciences, Clinical Medicine, Psychiatry, Medicin och hälsovetenskap, Klinisk medicin, Psykiatri, Natural Sciences, Computer and Information Sciences, Artificial Intelligence, Naturvetenskap, Data- och informationsvetenskap (Datateknik), Artificiell intelligens
Popis: The increasing prevalence of mental health problems coupled with limited access to professional support has prompted exploration of technological solutions. Large Language Models (LLMs) represent a potential tool to address these challenges, yet their capabilities in psychotherapeutic contexts remain unclear. This study examined the competencies of current LLMs in psychotherapy-related tasks including alignment with evidence-informed clinical standards in case formulation, treatment planning, and implementation. Using an exploratory mixed-methods design, we presented three clinical cases (depression, anxiety, stress) and 12 therapy-related prompts to seven LLMs: ChatGPT-4o, ChatGPT-4, Claude 3.5 Sonnet, Claude 3 Opus, Meta Llama 3.1, Google Gemini 1.5 Pro, and Microsoft Co-pilot. Responses were evaluated by five experienced clinical psychologists using quantitative ratings and qualitative feedback. No single model consistently produced high-quality responses across all tasks, though different models showed distinct strengths. Models performed better in structured tasks such as determining session length and discussing goal-setting but struggled with integrative clinical reasoning and treatment implementation. Higher-rated responses demonstrated clinical humility, maintained therapeutic boundaries, and recognised therapy as collaborative. Current LLMs are more promising as supportive tools for clinicians than as therapeutic applications. This paper highlights key areas for development needed to enhance clinical reasoning abilities for effective mental health use.
Prístupová URL adresa: https://doi.org/10.1080/29974100.2025.2545258
Databáza: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doi.org/10.1080/29974100.2025.2545258#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Tan%20S
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.portal.research.lu.se.publications.f95288f1.4d96.43d7.b875.b57fcb3a3618
RelevancyScore: 1152
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1152.22692871094
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: AI meets psychology: an exploratory study of large language models’ competence in psychotherapy contexts
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sian+Tan%2C+Kean%22">Sian Tan, Kean</searchLink><br /><searchLink fieldCode="AR" term="%22Cervin%2C+Matti%22">Cervin, Matti</searchLink><br /><searchLink fieldCode="AR" term="%22Leman%2C+Patrick%22">Leman, Patrick</searchLink><br /><searchLink fieldCode="AR" term="%22Nielsen%2C+Kristopher%22">Nielsen, Kristopher</searchLink><br /><searchLink fieldCode="AR" term="%22Vasantha+Kumar%2C+Prashanth%22">Vasantha Kumar, Prashanth</searchLink><br /><searchLink fieldCode="AR" term="%22Medvedev%2C+Oleg+N%2E%22">Medvedev, Oleg N.</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Lund University, Faculty of Medicine, Department of Clinical Sciences, Lund, Section IV, Child and Adolescent Psychiatry, Innovations in pediatric mental health, Lunds universitet, Medicinska fakulteten, Institutionen för kliniska vetenskaper, Lund, Sektion IV, Barn- och ungdomspsykiatri, Innovations in pediatric mental health, Originator
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Journal of Psychology and AI</i>. 1(1):1-17
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Medical+and+Health+Sciences%22">Medical and Health Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Clinical+Medicine%22">Clinical Medicine</searchLink><br /><searchLink fieldCode="DE" term="%22Psychiatry%22">Psychiatry</searchLink><br /><searchLink fieldCode="DE" term="%22Medicin+och+hälsovetenskap%22">Medicin och hälsovetenskap</searchLink><br /><searchLink fieldCode="DE" term="%22Klinisk+medicin%22">Klinisk medicin</searchLink><br /><searchLink fieldCode="DE" term="%22Psykiatri%22">Psykiatri</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+Sciences%22">Natural Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+and+Information+Sciences%22">Computer and Information Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Naturvetenskap%22">Naturvetenskap</searchLink><br /><searchLink fieldCode="DE" term="%22Data-+och+informationsvetenskap+%28Datateknik%29%22">Data- och informationsvetenskap (Datateknik)</searchLink><br /><searchLink fieldCode="DE" term="%22Artificiell+intelligens%22">Artificiell intelligens</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: The increasing prevalence of mental health problems coupled with limited access to professional support has prompted exploration of technological solutions. Large Language Models (LLMs) represent a potential tool to address these challenges, yet their capabilities in psychotherapeutic contexts remain unclear. This study examined the competencies of current LLMs in psychotherapy-related tasks including alignment with evidence-informed clinical standards in case formulation, treatment planning, and implementation. Using an exploratory mixed-methods design, we presented three clinical cases (depression, anxiety, stress) and 12 therapy-related prompts to seven LLMs: ChatGPT-4o, ChatGPT-4, Claude 3.5 Sonnet, Claude 3 Opus, Meta Llama 3.1, Google Gemini 1.5 Pro, and Microsoft Co-pilot. Responses were evaluated by five experienced clinical psychologists using quantitative ratings and qualitative feedback. No single model consistently produced high-quality responses across all tasks, though different models showed distinct strengths. Models performed better in structured tasks such as determining session length and discussing goal-setting but struggled with integrative clinical reasoning and treatment implementation. Higher-rated responses demonstrated clinical humility, maintained therapeutic boundaries, and recognised therapy as collaborative. Current LLMs are more promising as supportive tools for clinicians than as therapeutic applications. This paper highlights key areas for development needed to enhance clinical reasoning abilities for effective mental health use.
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doi.org/10.1080/29974100.2025.2545258" linkWindow="_blank">https://doi.org/10.1080/29974100.2025.2545258</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.portal.research.lu.se.publications.f95288f1.4d96.43d7.b875.b57fcb3a3618
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/29974100.2025.2545258
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 1
    Subjects:
      – SubjectFull: Medical and Health Sciences
        Type: general
      – SubjectFull: Clinical Medicine
        Type: general
      – SubjectFull: Psychiatry
        Type: general
      – SubjectFull: Medicin och hälsovetenskap
        Type: general
      – SubjectFull: Klinisk medicin
        Type: general
      – SubjectFull: Psykiatri
        Type: general
      – SubjectFull: Natural Sciences
        Type: general
      – SubjectFull: Computer and Information Sciences
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Naturvetenskap
        Type: general
      – SubjectFull: Data- och informationsvetenskap (Datateknik)
        Type: general
      – SubjectFull: Artificiell intelligens
        Type: general
    Titles:
      – TitleFull: AI meets psychology: an exploratory study of large language models’ competence in psychotherapy contexts
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sian Tan, Kean
      – PersonEntity:
          Name:
            NameFull: Cervin, Matti
      – PersonEntity:
          Name:
            NameFull: Leman, Patrick
      – PersonEntity:
          Name:
            NameFull: Nielsen, Kristopher
      – PersonEntity:
          Name:
            NameFull: Vasantha Kumar, Prashanth
      – PersonEntity:
          Name:
            NameFull: Medvedev, Oleg N.
      – PersonEntity:
          Name:
            NameFull: Lund University, Faculty of Medicine, Department of Clinical Sciences, Lund, Section IV, Child and Adolescent Psychiatry, Innovations in pediatric mental health, Lunds universitet, Medicinska fakulteten, Institutionen för kliniska vetenskaper, Lund, Sektion IV, Barn- och ungdomspsykiatri, Innovations in pediatric mental health, Originator
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 04
              M: 09
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: LU_SWEPUB
          Numbering:
            – Type: volume
              Value: 1
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Psychology and AI
              Type: main
ResultId 1