Can Conversational AI Counsel for Change? A Theory-Driven Approach to Supporting Dietary Intentions in Ambivalent Individuals

2025-11-04

AI Summary

This study addresses the common issue of intention ambivalence in dietary behavior change. Method: We propose a theory-driven conversational AI intervention that systematically integrates the Transtheoretical Model (TTM) and Motivational Interviewing (MI) strategies into an open-source large language model (LLM). Our approach employs domain-adapted role modeling, theory-consistent prompt engineering, and few-shot fine-tuning to enhance the model’s fidelity and consistency in applying behavioral science principles. Contribution/Results: Experimental evaluation demonstrates that our system significantly strengthens users’ immediate intention to change dietary behavior (p < 0.01), outperforming baseline models. User assessments confirm high usability, comprehensibility, and perceived supportiveness. To our knowledge, this is the first work to achieve systematic integration of TTM and MI within LLM-based conversational interventions. It establishes a reproducible, interpretable paradigm for personalized digital health interventions in chronic disease prevention.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Intelligent User Interfaces
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

Adherence to healthy diets reduces chronic illness risk, yet rates remain low. Large Language Models (LLMs) are increasingly used for health communication but often struggle to engage individuals with ambivalent intentions at a pivotal stage of the Transtheoretical Model (TTM). We developed CounselLLM, an open-source model enhanced through persona design and few-shot, domain-specific prompts grounded in TTM and Motivational Interviewing (MI). In controlled evaluations, CounselLLM showed stronger use of TTM subprocesses and MI affirmations than human counselors, with comparable linguistic robustness but expressed in more concrete terms. A user study then tested CounselLLM in an interactive counseling setting against a baseline system. While knowledge and perceptions did not change, participants'intentions for immediate dietary change increased significantly after interacting with CounselLLM. Participants also rated it as easy to use, understandable, and supportive. These findings suggest theory-driven LLMs can effectively engage ambivalent individuals and provide a scalable approach to digital counseling.

Problem

• Developing AI to counsel ambivalent individuals for dietary change
• Enhancing LLMs with psychological theories for health communication
• Addressing low adherence to healthy diets through scalable counseling

Innovation

• Developed CounselLLM with persona design
• Used TTM and Motivational Interviewing prompts
• Enhanced dietary intentions through interactive counseling