EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Aligning large language models for cognitive behavioral therapy: a proof-of-concept study

Yejin Kim, Chi-Hyun Choi, Selin Cho, Jy-Yong Sohn, Byung-Hoon Kim

Frontiers in Psychiatry · 03.09.2025 · 16

DOI: 10.3389/fpsyt.2025.1583739 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Psychiatry, online erschienen am 03.09.2025. Verfasst von Yejin Kim und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics and Data Science, Yonsei University, Seoul, Republic of Korea. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advancements in large language models (LLMs) have significantly impacted society, particularly with their ability to generate responses in natural language. However, their application to psychotherapy is limited due to the challenge of aligning LLM behavior with clinically appropriate responses. In this paper, we introduce LLM4CBT, designed to provide psychotherapy by adhering to professional therapeutic strategies, specifically within the framework of cognitive behavioral therapy (CBT). Our experimental results on real-world conversation data demonstrate that LLM4CBT aligns closely with the behavior of human expert therapists, exhibiting a higher frequency of desirable therapeutic behaviors compared to existing LLMs. Additionally, experiments on simulated conversation data show that LLM4CBT can effectively elicit automatic thoughts that patients unconsciously possess. Moreover, LLM4CBT is able to pause and wait until they are prepared to participate in the discussion for patients experiencing difficulty in engaging with the intervention, rather than continuously pressing with questions. The results demonstrate potential possibilities on designing LLM-based CBT therapists by aligning the model with appropriate instructions.

Schlagwörter

Stichwörter der Autor:innen

alignmentartificial intelligencecognitive behavior therapylarge language modelprompt

Autor:innen und Institutionen

  • Department of Statistics and Data Science, Yonsei University, Seoul, Republic of Korea.
  • EverEx, Seoul, Republic of Korea.
  • Department of Biotechnology, Yonsei University, Seoul, Republic of Korea.
  • Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Republic of Korea.
  • Department of Psychiatry, Yonsei University College of Medicine, Seoul, Republic of Korea.
  • Institute of Behavioral Sciences in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.

Zitieren

APA

Kim, Y., Choi, C. H., Cho, S., Sohn, J. Y., & Kim, B. H. (2025). Aligning large language models for cognitive behavioral therapy: a proof-of-concept study. Frontiers in Psychiatry, 16. https://doi.org/10.3389/fpsyt.2025.1583739

Vancouver

Kim Y, Choi CH, Cho S, Sohn JY, Kim BH. Aligning large language models for cognitive behavioral therapy: a proof-of-concept study. Frontiers in Psychiatry. 2025;16. doi:10.3389/fpsyt.2025.1583739

BibTeX
@article{Kim2025,
  author = {Kim, Yejin and Choi, Chi-Hyun and Cho, Selin and Sohn, Jy-Yong and Kim, Byung-Hoon},
  title = {Aligning large language models for cognitive behavioral therapy: a proof-of-concept study},
  journal = {Frontiers in Psychiatry},
  year = {2025},
  volume = {16},
  doi = {10.3389/fpsyt.2025.1583739}
}
Kostenlos starten →