Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation

Abstract

Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model’s prediction. Therefore, CFs can be used as (i) interventions for abnormality prevention and (ii) augmented data for training robust models. we conduct a comprehensive evaluation of CF generation using large language models (LLMs), including GPT-4 (zero-shot and few-shot) and two open-source models-BioMistral-7B and LLaMA-3.1-8B-in both pretrained and fine-tuned configurations. Using the multimodal AI-READI clinical dataset, we assess CFs across three dimensions: intervention quality, feature diversity, and augmentation effectiveness. Fine-tuned LLMs, particularly LLaMA-3.1-8B, produce CFs with high plausibility (up to 99%), strong validity (up to 0.99), and realistic, behaviorally modifiable feature adjustments. When used for data augmentation under controlled label-scarcity settings, LLM-generated CFs substantially restore classifier performance, yielding an average 20% F1 recovery across three scarcity scenarios. Compared with optimization-based baselines such as DiCE, CFNOW, and NICE, LLMs offer a flexible, model-agnostic approach that generates more clinically plausible, behaviorally actionable and semantically coherent counterfactuals. Overall, this work demonstrates the promise of LLM-driven counterfactuals for both interpretable intervention design and data-efficient model training in sensor-based digital health.

Shovito Barua Soumma

Graduate Research Associate

I am a Ph.D. candidate at Arizona State University. I work as a Graduate Research Associate at Embedded Machine Intelligence Lab (EMIL) under the supervision of Dr. Hassan Ghasemzadeh.

Asiful Arefeen

Graduate Research Assistant

I am a PhD student at Arizona State University (ASU). I am working under the supervision of Professor Hassan Ghasemzadeh at the Embedded Machine Intelligence Lab (EMIL). I am interested in explainable AI, using AI to generate interventions in digital health, machine learning, passive sensing and mobile health. I received a BS in Electrical & Electronic Engineering from Bangladesh University of Engineering & Technology (BUET) in 2019 and an MS in Biomedical Informatics from Arizona State University in 2023.

Hassan Ghasemzadeh

Director

Hassan Ghasemzadeh is a Professor of Biomedical Informatics at Arizona State University (ASU).