Leveraging large language models to assess therapeutic technique diversity and its associations with the therapeutic alliance and outcome.

IF 3.8 1区心理学 Q2 PSYCHOLOGY, CLINICAL

Psychotherapy Research Pub Date : 2026-06-23 DOI:10.1080/10503307.2026.2689633

Amir Eliassaf, Yael Bar-Shachar, Aya Shamir, Dana Atzil-Slonim

{"title":"Leveraging large language models to assess therapeutic technique diversity and its associations with the therapeutic alliance and outcome.","authors":"Amir Eliassaf, Yael Bar-Shachar, Aya Shamir, Dana Atzil-Slonim","doi":"10.1080/10503307.2026.2689633","DOIUrl":null,"url":null,"abstract":"Objective: This study employed a novel methodology that leverages a Large Language Model (LLM) to automatically detect and annotate therapists' interventions in psychotherapy transcripts, to examine therapists' Therapeutic Technique Diversity (TTD) and its associations with the working alliance and client functioning.Method: A dataset of 872 transcribed psychotherapy sessions was analyzed. Therapists' interventions were annotated using a transformer-based model. TTD was quantified using Shannon's entropy index to calculate the diversity of the interventions. Multilevel regression models examined TTD changes within sessions, within dyads (between sessions), and between dyads, and its associations with the Working Alliance Inventory (WAI) and the Outcome Rating Scale (ORS).Results: TTD significantly increased both within and between sessions. A higher TTD within-dyad was positively associated with WAI and ORS scores, although the association with ORS did not remain significant after accounting for session number. No between-dyads effects of TTD were found.Conclusion: TTD emerged as a dynamic feature of therapist behavior associated with the quality of the therapeutic alliance and treatment outcome. These findings underscore the importance of maintaining a diverse repertoire of interventions and highlight the potential of LLMs to capture granular therapeutic processes at scale.","PeriodicalId":48159,"journal":{"name":"Psychotherapy Research","volume":" ","pages":"1-14"},"PeriodicalIF":3.8000,"publicationDate":"2026-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Psychotherapy Research","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1080/10503307.2026.2689633","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHOLOGY, CLINICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: This study employed a novel methodology that leverages a Large Language Model (LLM) to automatically detect and annotate therapists' interventions in psychotherapy transcripts, to examine therapists' Therapeutic Technique Diversity (TTD) and its associations with the working alliance and client functioning.

Method: A dataset of 872 transcribed psychotherapy sessions was analyzed. Therapists' interventions were annotated using a transformer-based model. TTD was quantified using Shannon's entropy index to calculate the diversity of the interventions. Multilevel regression models examined TTD changes within sessions, within dyads (between sessions), and between dyads, and its associations with the Working Alliance Inventory (WAI) and the Outcome Rating Scale (ORS).

Results: TTD significantly increased both within and between sessions. A higher TTD within-dyad was positively associated with WAI and ORS scores, although the association with ORS did not remain significant after accounting for session number. No between-dyads effects of TTD were found.

Conclusion: TTD emerged as a dynamic feature of therapist behavior associated with the quality of the therapeutic alliance and treatment outcome. These findings underscore the importance of maintaining a diverse repertoire of interventions and highlight the potential of LLMs to capture granular therapeutic processes at scale.

查看原文本刊更多论文

利用大型语言模型来评估治疗技术的多样性及其与治疗联盟和结果的关联。

目的：本研究采用一种新颖的方法，利用大语言模型（LLM）来自动检测和注释治疗师在心理治疗记录中的干预行为，以检验治疗师的治疗技术多样性（TTD）及其与工作联盟和来访者功能的关系。方法：对872个心理治疗记录数据集进行分析。治疗师的干预使用基于变压器的模型进行注释。利用Shannon熵指数对TTD进行量化，计算干预措施的多样性。多水平回归模型检验了TTD在治疗组内、组内（治疗组之间）和组间的变化，以及其与工作联盟量表（WAI）和结果评定量表（ORS）的关系。结果：TTD在治疗期间和治疗间隙均显著增加。双年内较高的TTD与WAI和ORS评分呈正相关，尽管在计入会话数后与ORS的关联并不显著。未发现TTD的双元间效应。结论：TTD是治疗师行为的动态特征，与治疗联盟的质量和治疗结果相关。这些发现强调了维持多种干预措施的重要性，并强调了llm在大规模捕获颗粒治疗过程中的潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Psychotherapy Research PSYCHOLOGY, CLINICAL-

CiteScore

7.80

自引率

10.30%

发文量

期刊介绍： Psychotherapy Research seeks to enhance the development, scientific quality, and social relevance of psychotherapy research and to foster the use of research findings in practice, education, and policy formulation. The Journal publishes reports of original research on all aspects of psychotherapy, including its outcomes, its processes, education of practitioners, and delivery of services. It also publishes methodological, theoretical, and review articles of direct relevance to psychotherapy research. The Journal is addressed to an international, interdisciplinary audience and welcomes submissions dealing with diverse theoretical orientations, treatment modalities.