SenseCF: LLM-Prompted Counterfactuals for Intervention and Sensor Data Augmentation
This work addresses the need for human-centric explainability and robust model training in clinical and physiological prediction tasks, though it is incremental as it applies existing LLM techniques to a specific domain.
The paper tackles the problem of generating counterfactual explanations for machine learning predictions by using large language models (LLMs) in zero-shot and few-shot settings, achieving high plausibility (up to 99%) and validity (up to 0.99) on stress and heart disease datasets, and improves downstream classifier accuracy by an average of 5% when used for data augmentation.
Counterfactual explanations (CFs) offer human-centric insights into machine learning predictions by highlighting minimal changes required to alter an outcome. Therefore, CFs can be used as (i) interventions for abnormality prevention and (ii) augmented data for training robust models. In this work, we explore large language models (LLMs), specifically GPT-4o-mini, for generating CFs in a zero-shot and three-shot setting. We evaluate our approach on two datasets: the AI-Readi flagship dataset for stress prediction and a public dataset for heart disease detection. Compared to traditional methods such as DiCE, CFNOW, and NICE, our few-shot LLM-based approach achieves high plausibility (up to 99%), strong validity (up to 0.99), and competitive sparsity. Moreover, using LLM-generated CFs as augmented samples improves downstream classifier performance (an average accuracy gain of 5%), especially in low-data regimes. This demonstrates the potential of prompt-based generative techniques to enhance explainability and robustness in clinical and physiological prediction tasks. Code base: github.com/shovito66/SenseCF.