Human-AI Alignment of Multimodal Large Language Models with Speech-Language Pathologists in Parent-Child Interactions

TL;DR

This paper demonstrates how multimodal large language models can be aligned with speech-language pathologists to interpret parent-child interactions, achieving high accuracy in assessing joint attention through expert-informed prompts and structured behavioural cues.

Contribution

It introduces a two-stage MLLM system aligned with SLP reasoning, providing a novel approach to automated behavioural assessment in parent-child interactions.

Findings

MLLMs achieved up to 85% accuracy in cue extraction

Over 75% average precision in expert judgement simulation

Guidelines for designing SLP-aligned MLLM systems

Abstract

Joint attention is a critical marker of early social-communicative development, yet remains difficult for caregivers to assess without expert guidance. In this work, we explore how multimodal large language models (MLLMs) can be aligned with the reasoning processes of speech-language pathologists (SLPs) to support the interpretation of everyday parent-child interactions. We conducted in-depth interviews and video annotation studies with three experienced SLPs to uncover how they evaluate joint attention based on three core behavioural cues: gaze, action, and vocalisation. Using these insights, we developed a two-stage MLLM-based system that first extracts fine-grained behavioural descriptions from video segments and then judge joint attention quality using expert-aligned prompts. Our evaluation across 26 parent-child interaction videos shows that MLLMs can achieve up to 85% accuracy in perceptual cue extraction and over 75% average precision in simulating expert judgement. We further propose design guidelines for building MLLM-based behaviour observation-judgement systems that align with SLPs, emphasising the structuring of behavioural cues, the construction of exemplar libraries grounded in expert annotations, and the need to personalise system responses based on developmental stage and neurotypical or atypical presentation. This work provides structured behavioural cues derived from SLP expertise, demonstrates the feasibility of aligning SLPs observation and judgement using MLLMs, and offers practical design guidelines for building aligned systems to support parent-child interaction analysis.