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

TL;DR

This paper introduces CounselLLM, a theory-driven conversational AI designed to support dietary change in ambivalent individuals, demonstrating its effectiveness in increasing immediate dietary intentions and engaging users in health counseling.

Contribution

Developed CounselLLM, an open-source LLM enhanced with TTM and MI principles, showing improved engagement and intention change in dietary counseling compared to baseline systems.

Findings

CounselLLM increased participants' immediate dietary change intentions.

Participants rated CounselLLM as easy to use and supportive.

CounselLLM used more TTM subprocesses and MI affirmations than human counselors.

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.