What is Explainability vs interpretability?
Interpretability is how far a person can understand how a model produces its outputs from its structure, while explainability is the ability to give understandable reasons for a specific output, often after the fact using separate techniques. The terms are used loosely and sometimes interchangeably.
A simple decision tree is interpretable by design; a large neural network usually needs explanation methods to describe individual outputs. Which level is needed depends on the use: decisions affecting people's rights call for clearer reasons than a content recommendation. Transparency and explainability also appear among the OECD AI Principles.
Source: OECD AI Principles. Last reviewed . General information, not legal advice.