Explainable Artificial Intelligence (XAI) for Trustworthy Intelligent Systems
DOI:
https://doi.org/10.66421/int.j.datasci.intell.syst6Keywords:
Explainable AI, Interpretability, Trustworthy Systems, Machine Learning Transparency, XAI Techniques.Abstract
Explainable Artificial Intelligence (XAI) has become a foundational requirement for the
development of transparent, fair, and trustworthy intelligent systems. As AI-driven
algorithms grow increasingly complex, the interpretability of their decisions becomes
essential to establish user trust, reduce bias, and comply with emerging regulatory
frameworks. This paper provides a comprehensive overview of XAI approaches, including
post-hoc and intrinsic interpretability methods, and discusses their application in mission
critical domains. The study highlights the challenges associated with balancing accuracy
and explainability, evaluates contemporary XAI techniques, and outlines future research
directions. The findings emphasize that robust, human-centered explainability is
indispensable for the development of reliable and ethically aligned intelligent systems.
References
Ribeiro et al. (2016) proposed LIME for local interpretability.
Lundberg & Lee (2017) introduced SHAP for unified feature attribution.
Doshi-Velez & Kim (2017) discussed interpretability evaluation frameworks.
Adadi & Berrada (2018) provided a comprehensive XAI taxonomy.
Guidotti et al. (2019) surveyed explanation methods for black-box models.
Samek et al. (2017) highlighted visual explanation techniques for deep learning.
Lipton (2018) distinguished interpretability concepts and pitfalls.
Molnar (2020) explored interpretable machine learning methodologies.
Miller (2019) emphasized human-centered explainability principles.
Holzinger et al. (2020) reviewed XAI for medical diagnostics.
Arrieta et al. (2020) defined XAI principles for trustworthy AI.
Tjoa & Guan (2020) analyzed XAI applications in deep learning.
Gunning (2017) introduced DARPA’s XAI program for explainable models.
Caruana et al. (2015) demonstrated interpretable medical models.
Montavon et al. (2019) studied Layer-wise Relevance Propagation (LRP).
Preece (2018) examined challenges of XAI in autonomous systems.
Kim et al. (2018) introduced TCAV for concept-based interpretability.
Wachter et al. (2017) proposed counterfactual explanations for transparency.
Zhang & Chen (2020) studied fidelity metrics in XAI.
Kaur et al. (2020) evaluated human trust in AI explanations.
Ahmad, N. R. (2025). Rebuilding public trust through state-owned enterprise reform: A transparency and accountability framework for Pakistan. International Journal of Business and Economic Analysis. https://doi.org/10.24088/IJBEA-2025-103004
Ahmad, N. R. (2024). AI-enabled public governance in developing states: Service delivery gains, accountability risks, and a practical risk-based regulatory model. https://doi.org/10.52152/wja5db40
Sohail, N., Haque, A., Aziz, S., & Maruf, T. I. (2023). Impact of diffusion of innovation among Pakistani consumers’ adoption of halal cosmetics. South East Asia Journal of Contemporary Business, Economics and Law, 30(2), 39–50. https://doi.org/10.5281/zenodo.13798671
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Journal of Data Sciences and Intelligent Systems

This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles are published under the Creative Commons Attribution 4.0 (CC BY 4.0) License. Users may share, copy, adapt, and distribute the work for any purpose, provided proper credit is given to the original author(s) and source. Authors retain copyright.
