Saved in:
Bibliographic Details
Main Authors: Hu, Run-ze, Yang, Yang, Yang, Yi-hang, Kong, Jing-qi, Luo, Jia-hui, Yang, Wen-yu, Chen, Jing, Liu, Jing-yao, Zeng, Hui-qun, Zhang, Lei, Liu, Zheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.15446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918252451463168
author Hu, Run-ze
Yang, Yang
Yang, Yi-hang
Kong, Jing-qi
Luo, Jia-hui
Yang, Wen-yu
Chen, Jing
Liu, Jing-yao
Zeng, Hui-qun
Zhang, Lei
Liu, Zheng
author_facet Hu, Run-ze
Yang, Yang
Yang, Yi-hang
Kong, Jing-qi
Luo, Jia-hui
Yang, Wen-yu
Chen, Jing
Liu, Jing-yao
Zeng, Hui-qun
Zhang, Lei
Liu, Zheng
contents Background: Motivational interviewing (MI) is an effective counseling approach for promoting health behavior change, but its impact is constrained by the need for highly trained human counselors. Objective: This study aimed to explore a scalable alternative by developing and evaluating Large Language Models for Motivational Interviewing (MI-LLMs). Methods: We first curated five Chinese psychological counseling corpora and, using GPT-4 with an MI-informed prompt, transcribed multi-turn dialogues from the two highest-quality datasets (CPsyCounD and PsyDTCorpus) into 2,040 MI-style counseling conversations, of which 2,000 were used for training and 40 for testing. Three Chinese-capable open-source LLMs (Baichuan2-7B-Chat, ChatGLM-4-9B-Chat and Llama-3-8B-Chinese-Chat-v2) were fine-tuned on this corpus and were named as MI-LLMs. We evaluated MI-LLMs using round-based automatic metrics and expert manual coding with the Motivational Interviewing Treatment Integrity (MITI) Coding Manual 4.2.1. Results: Across all three models, fine-tuning substantially improved BLEU-4 and ROUGE scores compared with the base models, and manual coding showed that MI-LLMs achieved technical and relational global scores, and MI-adherent ratios that approached those of real MI dialogues, although complex reflections and reflection-to-question ratios remained less frequent. Conclusions: These findings provide initial evidence that MI-oriented fine-tuning can endow general-purpose LLMs with core MI-consistent counseling behaviors, suggesting a scalable pathway toward AI-assisted health behavior change support while underscoring the need for further work on data scale, complex MI skills and real-world intervention trials.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15446
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward expert-level motivational interviewing for health behavior improvement with LLMs
Hu, Run-ze
Yang, Yang
Yang, Yi-hang
Kong, Jing-qi
Luo, Jia-hui
Yang, Wen-yu
Chen, Jing
Liu, Jing-yao
Zeng, Hui-qun
Zhang, Lei
Liu, Zheng
Computation and Language
Background: Motivational interviewing (MI) is an effective counseling approach for promoting health behavior change, but its impact is constrained by the need for highly trained human counselors. Objective: This study aimed to explore a scalable alternative by developing and evaluating Large Language Models for Motivational Interviewing (MI-LLMs). Methods: We first curated five Chinese psychological counseling corpora and, using GPT-4 with an MI-informed prompt, transcribed multi-turn dialogues from the two highest-quality datasets (CPsyCounD and PsyDTCorpus) into 2,040 MI-style counseling conversations, of which 2,000 were used for training and 40 for testing. Three Chinese-capable open-source LLMs (Baichuan2-7B-Chat, ChatGLM-4-9B-Chat and Llama-3-8B-Chinese-Chat-v2) were fine-tuned on this corpus and were named as MI-LLMs. We evaluated MI-LLMs using round-based automatic metrics and expert manual coding with the Motivational Interviewing Treatment Integrity (MITI) Coding Manual 4.2.1. Results: Across all three models, fine-tuning substantially improved BLEU-4 and ROUGE scores compared with the base models, and manual coding showed that MI-LLMs achieved technical and relational global scores, and MI-adherent ratios that approached those of real MI dialogues, although complex reflections and reflection-to-question ratios remained less frequent. Conclusions: These findings provide initial evidence that MI-oriented fine-tuning can endow general-purpose LLMs with core MI-consistent counseling behaviors, suggesting a scalable pathway toward AI-assisted health behavior change support while underscoring the need for further work on data scale, complex MI skills and real-world intervention trials.
title Toward expert-level motivational interviewing for health behavior improvement with LLMs
topic Computation and Language
url https://arxiv.org/abs/2512.15446