The increasing adoption of artificial intelligence in oral and maxillofacial radiology has introduced powerful data-driven models capable of assisting in image interpretation, classification, and decision support. However, the inherent opacity of many advanced models, particularly deep learning systems, poses challenges related to clinical trust, accountability, and safe integration into diagnostic workflows. Explainable artificial intelligence (XAI) addresses these concerns by providing methods that make AI decisions transparent, interpretable, and clinically understandable. This chapter explores the conceptual foundations, methodologies, and clinical relevance of XAI in oral and maxillofacial radiology. It discusses key explainability approaches, including model-intrinsic interpretability, post hoc explanation techniques, visualization-based methods, feature attribution frameworks, and uncertainty-aware explanations. This chapter emphasizes how XAI supports validation of AI outputs, enhances clinician confidence, facilitates error detection, and aligns AI-assisted decisions with established radiological reasoning. Applications of XAI in CBCT analysis, jaw lesion classification, implant planning, and educational settings are highlighted. By integrating explainability with performance, XAI serves as a critical bridge between advanced artificial intelligence models and responsible, transparent clinical practice in oral and maxillofacial radiology.