Explainable AI: XAI-Guided Context-Aware Data Augmentation

TL;DR

This paper introduces a novel explainability-guided data augmentation framework that improves model accuracy and robustness, especially for low-resource languages, by selectively modifying features based on explainability insights.

Contribution

The paper presents a new XAI-guided, context-aware data augmentation method that refines augmented data through iterative feedback, outperforming existing techniques in accuracy and interpretability.

Findings

XAI-Guided augmentation improves accuracy by up to 8.1%.

The method outperforms conventional augmentation techniques by 4.8-5%.

It enhances model robustness and interpretability.

Abstract

Explainable AI (XAI) has emerged as a powerful tool for improving the performance of AI models, going beyond providing model transparency and interpretability. The scarcity of labeled data remains a fundamental challenge in developing robust and generalizable AI models, particularly for low-resource languages. Conventional data augmentation techniques introduce noise, cause semantic drift, disrupt contextual coherence, lack control, and lead to overfitting. To address these challenges, we propose XAI-Guided Context-Aware Data Augmentation. This novel framework leverages XAI techniques to modify less critical features while selectively preserving most task-relevant features. Our approach integrates an iterative feedback loop, which refines augmented data over multiple augmentation cycles based on explainability-driven insights and the model performance gain. Our experimental results demonstrate that XAI-SR-BT and XAI-PR-BT improve the accuracy of models on hate speech and sentiment analysis tasks by 6.6% and 8.1%, respectively, compared to the baseline, using the Amharic dataset with the XLM-R model. XAI-SR-BT and XAI-PR-BT outperform existing augmentation techniques by 4.8% and 5%, respectively, on the same dataset and model. Overall, XAI-SR-BT and XAI-PR-BT consistently outperform both baseline and conventional augmentation techniques across all tasks and models. This study provides a more controlled, interpretable, and context-aware solution to data augmentation, addressing critical limitations of existing augmentation techniques and offering a new paradigm shift for leveraging XAI techniques to enhance AI model training.