Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Cognitive Therapy01:25

Cognitive Therapy

1.4K
Cognitive therapy, pioneered by Aaron T. Beck in the 1960s, is a structured approach to addressing psychological distress by focusing on the influence of thoughts on emotions and behaviors. All cognitive therapies involve the basic assumption that human beings have control over their feelings, and that how individuals feel about something depends on how they think about it. Unlike psychoanalytic methods that delve into unconscious processes or humanistic approaches emphasizing...
1.4K
Modeling in Therapy01:26

Modeling in Therapy

652
Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
652
Language and Cognition01:27

Language and Cognition

928
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
928
Psychotherapy01:28

Psychotherapy

605
Psychotherapy is a versatile, nonmedical approach aimed at helping individuals address emotional, behavioral, and interpersonal issues to enhance their overall well-being. It can involve one-on-one sessions, couples counseling, or small group discussions with a therapist. The therapeutic process includes various techniques such as open discussion, interpretation of thoughts and behaviors, active listening, positive reinforcement, and role modeling. Psychotherapy aims to support individuals in...
605
Higher Mental Functions of the Brain: Language01:10

Higher Mental Functions of the Brain: Language

4.0K
Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
4.0K
Interpersonal Psychotherapy01:25

Interpersonal Psychotherapy

523
Interpersonal psychotherapy (IPT) is a structured, time-limited therapeutic approach initially developed to treat depression. It integrates key concepts from psychodynamic, humanistic, and cognitive-behavioral therapies, making it a uniquely eclectic framework. The therapy is rooted in the interpersonal theories of Adolph Meyer and Harry Stack Sullivan, as well as John Bowlby's attachment theory, and focuses on the interplay between interpersonal relationships and emotional well-being.
523

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

cpm: A python library for theory-driven modelling in computational psychiatry.

PLoS computational biology·2026
Same author

Acute Anxiety Selectively Enhances Value-Free Random Exploration through Frontoparietal Engagement.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2026
Same author

AI-driven mental health decision support linked to clinician resilience and preparedness.

Frontiers in digital health·2026
Same author

When Collaboration Falters, Insensitivity to How Our Actions Affect Others Drives Inflated Self-evaluations.

Computational brain & behavior·2026
Same author

Metacognitive biases in anxiety-depression and compulsivity extend across perception and memory.

PLOS mental health·2026
Same author

Increased Baseline Pupil Size Linked to Uncertainty Avoidance in Decision Making.

The European journal of neuroscience·2026

Related Experiment Video

Updated: Mar 14, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

A cognitive layer architecture to support large-language model performance in psychotherapy interactions.

Max Rollwage1, Jessica McFadyen2, Keno Juchems2

  • 1Limbic, London, UK. rollwagm@gmail.com.

Nature Medicine
|March 13, 2026
PubMed
Summary

Large language models (LLMs) with a specialized cognitive layer architecture show promise in mental healthcare. These AI agents outperformed both standard LLMs and human therapists in delivering cognitive-behavioral therapy, improving patient well-being.

More Related Videos

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

454
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.8K

Related Experiment Videos

Last Updated: Mar 14, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

454
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.8K

Area of Science:

  • Artificial Intelligence in Healthcare
  • Clinical Psychology
  • Natural Language Processing

Background:

  • Clinician-patient interactions are central to mental healthcare.
  • The efficacy of large language models (LLMs) in patient-facing mental health support is largely unproven.
  • General-purpose LLMs lack specialized psychotherapeutic reasoning capabilities.

Purpose of the Study:

  • To introduce and evaluate a cognitive layer architecture that enhances LLMs with clinical psychotherapeutic reasoning.
  • To assess the performance of augmented LLMs against standalone LLMs and human clinicians in mental well-being sessions.
  • To investigate the real-world effectiveness and clinical impact of LLM-based AI therapeutics.

Main Methods:

  • A randomized, double-blind evaluation involving 227 participants interacting with therapy agents to generate mental well-being session transcripts.
  • Assessment of transcripts by 22 expert clinicians based on key cognitive-behavioral therapy competencies.
  • Analysis of 19,674 transcripts from a large-scale, real-world deployment supporting 8,920 users.

Main Results:

  • LLMs augmented with the cognitive layer architecture consistently outperformed standalone LLMs and human clinicians in delivering cognitive-behavioral therapy.
  • In real-world deployment, increased cognitive layer activation correlated with greater symptom improvement.
  • Higher cognitive layer activation was linked to an increased likelihood of long-term clinical recovery (approximately 10 weeks).

Conclusions:

  • A cognitive layer architecture can equip LLMs to deliver high-quality cognitive-behavioral therapy interactions.
  • AI-assisted therapeutics show potential for enhancing mental healthcare delivery.
  • Further research is warranted to explore the mechanisms and clinical efficacy of AI in mental well-being support.