Challenges and Future Perspectives in Explainable AI A Roadmap for New Scholars

Machine learning is transforming industries with its capabilities in prediction, recommendation, and decision support. However, the complexity of these systems often hides their inner workings, earning them the label "black box" models. This lack of transparency makes it challenging for users to understand both processes and outcomes, highlighting the need for Explainable Artificial Intelligence (XAI) to build trustworthy AI systems.This paper reviews existing literature and contributions on XAI, focusing on core concepts such as interpretability, exploitability, and intelligibility. We emphasize the importance of these aspects for fostering trust, explore the XAI lifecycle, and analyze taxonomies of XAI methods. Additionally, we discuss challenges in the field and propose future research directions, stressing responsible AI development. Our aim is to help novice researchers understand the XAI framework and apply it effectively to their work.