Also known as: Explainability (XAI) · Explainable AI (XAI) · XAI
Explainable AI (XAI) относится к ИИ-системам, методам или свойствам, которые делают важные факторы, стоящие за выходами, понятными людям. XAI поддерживает прозрачность, подотчетность, contestability и доверие, особенно в high-impact settings, где затронутым людям нужно понимать или оспаривать решения.
Explainability means enabling people affected by the outcome of an AI system to understand how it was arrived at. This entails providing easy-to-understand information to people affected by an AI system's outcome that can enable those adversely affected to challenge the outcome, notably - to the extent practicable - the factors and logic that led to an outcome. Notwithstanding, explainability can be achieved in different ways depending on the context (such as, the significance of the outcomes).
As defined by the OECD, explainability encompasses efforts to enable people affected by AI system outputs and outcomes to understand how they were arrived at. This entails providing easy-to-understand information to people affected by an AI system's outcome that can enable those adversely affected to challenge the outcome, notably - to the extent practicable - the factors and logic that led to an outcome.
A side-by-side comparison of Transparency and Explainable AI. Understand how broad stakeholder visibility differs from methods that make model outputs understandable.
A side-by-side comparison of Black Box Model and Explainable AI. Understand how lack of understandable internal reasoning differs from methods or properties used to make outputs understandable.
A side-by-side comparison of Explainable AI and Interpretability. Understand how explanation-oriented systems and methods relate to the human ability to understand model behavior.