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

2026-01-21

AI Summary

This work addresses the dual challenges of generating interpretable, actionable counterfactual explanations for health intervention design and enhancing sensor data under label scarcity. We propose a solution based on fine-tuning large language models (LLMs), specifically BioMistral-7B and LLaMA-3.1-8B, on the multimodal AI-READI clinical dataset. Our systematic evaluation demonstrates that the fine-tuned LLaMA-3.1-8B produces counterfactual explanations with 99% plausibility and 0.99 validity, while recovering an average of 20% F1 score across three label-scarce scenarios. These results significantly outperform baseline methods such as DiCE and CFNOW, highlighting the model’s dual utility in delivering clinically actionable guidance and effective data augmentation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

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 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. Impact: SenseCF fine-tunes an LLM to generate valid, representative counterfactual explanations and supplement minority class in an imbalanced dataset for improving model training and boosting model robustness and predictive performance

Problem

• counterfactual explanations
• health intervention design
• sensor data augmentation
• label scarcity
• model robustness

Innovation

• Counterfactual Explanations
• Fine-tuned LLMs
• Health Intervention Design
• Sensor Data Augmentation
• Model-Agnostic Interpretability