Year: 2024
Type: article
Abstract: Explainable Artificial Intelligence (XAI) has become a foundational requirement for thedevelopment of transparent, fair, and trustworthy intelligent systems. As AI-drivenalgorithms grow increasingly complex, the interpretability of their decisions becomesessential to establish user trust, reduce bias, and comply with emerging regulatoryframeworks. This paper provides a comprehensive overview of XAI approaches, includingpost-hoc and intrinsic interpretability methods, and discusses their application in missioncritical domains. The study highlights the challenges associated with balancing accuracyand explainability, evaluates contemporary XAI techniques, and outlines future researchdirections. The findings emphasize that robust, human-centered explainability isindispensable for the development of reliable and ethically aligned intelligent systems.
Authors: MuhammadSalmanRaza, Hina Farooq
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7220818157
