Benchmarking Motivational Interviewing Competence of Large Language Models

AI Summary

Both proprietary and open-source LLMs achieved fair to good MI competence on MITI assessments in handcrafted and real-world clinical transcripts.
Top models outperformed human experts on complex reflection percentage and reflection-to-question ratio, but excessive complex reflections may produce unnatural dialogue.
Psychiatrists could barely distinguish LLM from human responses, identifying LLMs with roughly 56% accuracy, supporting further validation for low-resource deployment.

AI Summary

While large language models (LLMs) can potentially generate MI-consistent therapist responses, their competence using MITI is not well-researched, especially in real-world clinical transcripts.

Basic summary

Eur Addict Res. 2026 Jul 4:1-18. doi: 10.1159/000553455. Online ahead of print.

ABSTRACT

INTRODUCTION: Motivational interviewing (MI) promotes behavioural change in substance use disorders. Its fidelity is measured using the Motivational Interviewing Treatment Integrity (MITI) framework. While large language models (LLMs) can potentially generate MI-consistent therapist responses, their competence using MITI is not well-researched, especially in real-world clinical transcripts. We aim to benchmark MI competence of proprietary and open-source models compared to human therapists in real-world transcripts and assess distinguishability from human therapists.

METHODS: We shortlisted 3 proprietary and 7 open-source LLMs from LMArena, evaluated performance using MITI 4.2 framework on two datasets (96 handcrafted model transcripts, 34 real-world clinical transcripts). We generated parallel LLM-therapist utterances iteratively for each transcript while keeping client responses static, and ranked performance using a composite ranking system with MITI components and verbosity. We conducted a distinguishability experiment with two independent psychiatrists to identify human-vs-LLM responses.

RESULTS: All 10 tested LLMs had fair (MITI global scores >3.5) to good (MITI global scores >4) competence across MITI measures, and three best-performing models (gemma-3-27b-it, gemini-2.5-pro, grok-3) were tested on real-world transcripts. All showed good competence, with LLMs outperforming human-expert in Complex Reflection percentage (39% vs 96%) and Reflection-Question ratio (1.2 vs >2.8). In the distinguishability experiment, psychiatrists identified LLM responses with only 56% accuracy, with d-prime: 0.17 and 0.25 for gemini-2.5-pro and gemma-3-27b-it respectively.

CONCLUSION: LLMs can achieve good MI proficiency in real-world clinical transcripts using MITI framework. However, high complex reflection percentage may result in a technically correct but unnatural conversation style. These findings suggest that even open-source LLMs are viable candidates for expanding MI counselling sessions in low-resource settings, warranting further rigorous clinical validation.

PMID:42400925 | DOI:10.1159/000553455

Document this CPD