Published Paper Details:

ABSTRACT: Artificial Intelligence (AI) has transformed many industries, but because AI models are inherently opaque, it can be difficult to understand how they make decisions. Explainable AI (XAI) aims to reduce this comprehension gap between AI models and humans by offering comprehensible justifications for actions made by AI. The importance of XAI in improving accountability, transparency, and trust in AI systems is examined in this study. It looks at a number of XAI strategies, such as model-specific strategies, post-hoc interpretability methodologies, and human-centred design concepts. The study also looks at the user-centred, legal, and ethical reasons for XAI adoption. It highlights the benefits and real-world applications of XAI through case studies in healthcare, finance, and autonomous systems. By addressing challenges and outlining future research directions, this study advocates for the widespread adoption of XAI to foster a more transparent and human-centred AI ecosystem. Keywords: Artificial Intelligence (AI), Explainable AI (XAI), Human Understanding.