Leveraging Multimodal Self-Consistency Reasoning in Coding Motivational Interviewing for Alcohol Use Reduction

TL;DR

This paper introduces a multimodal self-consistency reasoning method using audio-language models to automate coding of Motivational Interviewing sessions, improving robustness and accuracy over baseline approaches.

Contribution

It develops a novel multimodal self-consistency approach that integrates multiple reasoning trajectories from audio-language models for automatic MI coding.

Findings

Achieved 52.56% accuracy in MI coding, outperforming baseline methods.

Systematic ablation showed performance degradation when modules were removed.

Multimodal self-consistency enhances reliability of automatic MI coding.

Abstract

BACKGROUND: Coding Motivational Interviewing (MI) sessions is essential for understanding client behaviors and predicting outcomes, but it requires substantial time and labor from trained MI professionals. Recent advances in audio-language models (ALMs) offer new opportunities to automate MI coding by capturing multimodal behavioral signals. OBJECTIVE: This study aims to develop an automatic MI coding approach based on ALMs that analyzes raw audio input and integrates predictions from multiple reasoning trajectories using self-consistency to improve coding robustness. METHODS: We experimented with five recorded sessions from de-identified MI audio tapes. We deployed ALMs with four complementary analytic prompts to support utterance-level reasoning: analytic prompting for verbal cues, prosody-aware prompting for acoustic cues, evidence-scoring prompting for quantitative hypothesis testing, and comparative prompting for contrastive reasoning. Three stochastic samples were drawn for each prompt, generating 12 independent reasoning trajectories per utterance. Final predictions were determined by majority voting across all trajectories. RESULTS: Performance was evaluated using accuracy, precision, recall, and macro-F1 scores. The proposed multimodal self-consistency approach achieved 52.56% accuracy, 54.03% precision, 47.45% recall, and a macro-F1 score of 46.40%, exceeding baseline methods. Systematic ablation experiments that removed individual modules consistently degraded performance on the primary metrics. CONCLUSIONS: Multimodal self-consistency outperforms single-pass baseline prompting approaches for MI coding. These findings suggest that incorporating both what clients say and how they say it can support more reliable automatic MI coding.