Explainable AI: XAI-guided context-aware data augmentation
Mersha, Melkamu Abay Yigezu, Mesay Gemeda Tonja, Atnafu Lambebo Shakil, Hassan Iskander, Samer Kolesnikova, Olga Kalita, Jugal
Mersha, Melkamu Abay
Yigezu, Mesay Gemeda
Tonja, Atnafu Lambebo
Shakil, Hassan
Iskander, Samer
Kolesnikova, Olga
Kalita, Jugal
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
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.
Citation
M. A. Mersha et al., “Explainable AI: XAI-guided context-aware data augmentation,” Expert Syst Appl, vol. 289, p. 128364, Sep. 2025, doi: 10.1016/j.eswa.2025.128364.
Source
Expert Systems with Applications
Conference
Keywords
And natural language processing, Back translation, Data augmentation, Deep learning, Explainable artificial intelligence, Interpretable, Large language models, LLMs, Machine learning, Neural networks, Synonym replacement, XAI
Subjects
Source
Publisher
Elsevier