AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909620959707136 |
|---|---|
| author | Huang, Yinghui Jiang, Yuxuan Liu, Hui Cai, Yixin Li, Weiqing Hu, Xiangen |
| author_facet | Huang, Yinghui Jiang, Yuxuan Liu, Hui Cai, Yixin Li, Weiqing Hu, Xiangen |
| contents | Large language models (LLMs) like GPT-4 show potential for scaling motivational interviewing (MI) in addiction care, but require systematic evaluation of therapeutic capabilities. We present a computational framework assessing user-perceived quality (UPQ) through expected and unexpected MI behaviors. Analyzing human therapist and GPT-4 MI sessions via human-AI collaboration, we developed predictive models integrating deep learning and explainable AI to identify 17 MI-consistent (MICO) and MI-inconsistent (MIIN) behavioral metrics. A customized chain-of-thought prompt improved GPT-4's MI performance, reducing inappropriate advice while enhancing reflections and empathy. Although GPT-4 remained marginally inferior to therapists overall, it demonstrated superior advice management capabilities. The model achieved measurable quality improvements through prompt engineering, yet showed limitations in addressing complex emotional nuances. This framework establishes a pathway for optimizing LLM-based therapeutic tools through targeted behavioral metric analysis and human-AI co-evaluation. Findings highlight both the scalability potential and current constraints of LLMs in clinical communication applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17380 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing Huang, Yinghui Jiang, Yuxuan Liu, Hui Cai, Yixin Li, Weiqing Hu, Xiangen Computation and Language H.1.2; I.2.7 Large language models (LLMs) like GPT-4 show potential for scaling motivational interviewing (MI) in addiction care, but require systematic evaluation of therapeutic capabilities. We present a computational framework assessing user-perceived quality (UPQ) through expected and unexpected MI behaviors. Analyzing human therapist and GPT-4 MI sessions via human-AI collaboration, we developed predictive models integrating deep learning and explainable AI to identify 17 MI-consistent (MICO) and MI-inconsistent (MIIN) behavioral metrics. A customized chain-of-thought prompt improved GPT-4's MI performance, reducing inappropriate advice while enhancing reflections and empathy. Although GPT-4 remained marginally inferior to therapists overall, it demonstrated superior advice management capabilities. The model achieved measurable quality improvements through prompt engineering, yet showed limitations in addressing complex emotional nuances. This framework establishes a pathway for optimizing LLM-based therapeutic tools through targeted behavioral metric analysis and human-AI co-evaluation. Findings highlight both the scalability potential and current constraints of LLMs in clinical communication applications. |
| title | AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing |
| topic | Computation and Language H.1.2; I.2.7 |
| url | https://arxiv.org/abs/2505.17380 |