Explainable AI (XAI) /ɪkˈspleɪ.nə.bəl eɪ.aɪ/ noun — Explainable Artificial Intelligence (XAI) refers to a subset of AI techniques and models that are developed with the goal of making their internal decision-making processes transparent, understandable, and interpretable to humans.
XAI addresses one of the core challenges in modern AI: the “black box” nature of complex models, especially deep learning systems. By providing clear, human-readable explanations for why a model made a particular prediction or decision, XAI fosters trust, accountability, and ethical compliance, particularly in high-stakes domains such as healthcare, finance, criminal justice, and autonomous vehicles.
Techniques in XAI include feature importance analysis, saliency maps, LIME (Local Interpretable Model-agnostic Explanations), and SHAP (SHapley Additive exPlanations). These tools help both developers and end-users to interpret, debug, and validate AI systems, ensuring they align with human values and regulatory standards.
« Back to dictionary
