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

Stress Prevention and Stress Management Techniques VI01:30

Stress Prevention and Stress Management Techniques VI

Adopting a healthier lifestyle often requires overcoming significant challenges, but leveraging psychological, social, and cultural resources can facilitate meaningful change. Effective self-change hinges on understanding and applying key tools such as motivation and goal setting, which help sustain efforts toward long-term health benefits.
Motivation and Self-Determination
Motivation, the driving force behind behavior, plays a pivotal role at every stage of the change process. The research...
Motivational Bias01:25

Motivational Bias

Cognitive bias results from limitations in thinking and information processing, leading to systematic errors in judgment. Conversely, motivational bias stems from personal desires or emotions, causing distortions in perception to align with self-interest. Motivational bias influences how individuals perceive and attribute causes to events, often shaped by personal needs, goals, and self-esteem preservation. This bias can distort judgment, leading to inaccurate assessments of success, failure,...
Modeling in Therapy01:26

Modeling in Therapy

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 situations...
Models of Health Promotion and Illness Prevention II01:18

Models of Health Promotion and Illness Prevention II

The person's health status fluctuates continually, varying from being in good health to becoming ill and returning to being healthy. To understand the concept of illness prevention, there are two models. First, the health-illness continuum model is a graphic representation of an individual's wellness. It states that a person is considered healthy in the absence of physical disease and the presence of good emotional health.
The agent-host-environment model states that disease results from...
Models of Health Promotion and Illness Prevention I01:25

Models of Health Promotion and Illness Prevention I

A model is a theoretical way to understand a concept or an idea. Models can overcome barriers to health regardless of diverse economic and cultural backgrounds. In addition, models make the task easier by providing different ways to approach complex issues. There are two major health promotion models: the health belief model and the health promotion model.
The health belief model (HBM) attempts to predict health-related behavior in specific belief patterns. According to the HBM, a person's...
Methods of Medium Optimization01:28

Methods of Medium Optimization

Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...

You might also read

Related Articles

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

Sort by
Same author

Depression meets obesity: Co-occurrence patterns, temporal trends and socioeconomic correlates across 199 countries and territories.

General psychiatry·2026
Same author

Effect of autonomous motivation support on obesity prevention in early adolescents: a study protocol of cluster-randomized controlled trial based on the integrated SDT-TPB framework.

Trials·2026
Same author

Dynamic Predictors for Malignancy Risk of Follicular Thyroid Neoplasms: A Real-World, 10-Year Cohort Study.

Cancer medicine·2026
Same author

Healthcare Services and Burden of the Top Two Mental Disorders Among Women of Childbearing Age Across 204 Countries and Territories, 1990-2021.

Depression and anxiety·2026
Same author

Using machine learning to predict the small for gestational age and identify the important predictors: A real-world clinical cohort study in China.

PloS one·2026
Same author

Chatbot-based interventions for improvement of diet, physical activity, and tobacco use behaviors: protocol for a systematic review.

Systematic reviews·2026
Same journal

Remote Assessment of Parkinson Disease Using Deep Learning on Structured Mouse-Trace Data From Suspected Cases: Machine-Learning Pilot Feasibility Study.

JMIR formative research·2026
Same journal

Perspectives on Continuous Glucose Monitoring Among Adults with Type 2 Diabetes in the United Kingdom: Cross-Sectional Survey.

JMIR formative research·2026
Same journal

Real-World Engagement With a Generative AI Conversational Agent for Mental Health Support: Retrospective Descriptive Study.

JMIR formative research·2026
Same journal

Improving Models to Predict Care Utilization Using Machine Learning: Retrospective Observational Study.

JMIR formative research·2026
Same journal

Implementing a Commercial AI Fracture Detection Tool in Health Care Using the Non-Adoption, Abandonment, Scale-Up, Spread, and Sustainability Framework: A Formative Evaluation Study.

JMIR formative research·2026
Same journal

An Evaluation of the Usability and Feasibility of the 50K4Life Mobile App for Delivering Walking Challenges to Public School Administrative Employees: Beta Testing Study.

JMIR formative research·2026
See all related articles
  1. Home
  3. Fine-tuning Large Language Models For Motivational Interviewing In Health Behavior Change: Development And Evaluation Study.
  1. Home
  3. Fine-tuning Large Language Models For Motivational Interviewing In Health Behavior Change: Development And Evaluation Study.

Related Experiment Video

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

Fine-Tuning Large Language Models for Motivational Interviewing in Health Behavior Change: Development and Evaluation

Runze Hu1, Yang Yang1, Yihang Yang1

  • 1Department of Maternal and Child Health, School of Public Health, Peking University, No. 38 Xueyuan Road, Haidian District, Beijing, 100191, China, 86 010-82801222.

JMIR Formative Research
|June 24, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

Fine-tuning large language models (LLMs) with motivational interviewing (MI) principles improved their ability to generate Chinese counseling responses. While these MI-LLMs show promise for scalable support, they require further development to match human counselor fidelity.

Keywords:
behavior changefine-tuninghealth educationlarge language modelsmotivational interviewing

Related Experiment 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

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Behavioral Science

Background:

  • Motivational interviewing (MI) is effective for health behavior change but limited by counselor scalability.
  • Large language models (LLMs) offer a potential solution for scalable MI support, yet Chinese resources and fidelity evaluations are scarce.

Purpose of the Study:

  • To develop Chinese motivational interviewing large language models (MI-LLMs).
  • To evaluate if MI-focused fine-tuning enhances LLM generation of MI-consistent counseling responses.

Main Methods:

  • Curated and selected Chinese psychological counseling datasets (CPsyCounD, PsyDTCorpus).
  • Generated 2040 MI-style dialogs using GPT-4 for fine-tuning three open-source Chinese LLMs (Baichuan2, ChatGLM-4, Llama-3).
  • Evaluated MI-LLMs using automatic metrics (BLEU-4, ROUGE) and manual coding against real MI dialogs via the Motivational Interviewing Treatment Integrity Coding Manual.

Main Results:

  • Fine-tuning significantly improved automatic evaluation scores (BLEU-4, ROUGE) for all LLMs.
  • MI-LLMs achieved global scores and MI-adherence ratios comparable to real MI dialogs, with ChatGLM-4-based MI-LLM performing strongest.
  • MI-LLMs generated fewer complex reflections and had lower reflection-to-question ratios than human counselors.

Conclusions:

  • MI-focused fine-tuning enables Chinese LLMs to adopt core MI counseling behaviors, offering a scalable resource development approach.
  • Current MI-LLMs are early-stage tools for supporting, not replacing, human counselors.
  • Future research should focus on expanding training data, enhancing complex reflection skills, and evaluating real-world effectiveness, acceptability, and safety.