Explainability

How it is used

In research it appears as XAI (explainable AI). It matters in credit, insurance, hiring and medicine, where people may need a reason for a decision. Common methods include SHAP and LIME. Often used alongside interpretability, which focuses on how a model works inside.

Example sentences

1. For loan decisions explainability matters a lot, because customers can ask for the main reasons behind a rejection.

2. The explainability report shows that the postcode had too much influence on the score.

Common collocations

• model explainability
• explainability tools
• explainable AI
• feature attribution

Related terms

• fairnessThe goal that a model treats different groups of people equitably, for example by giving similar error rates or approval rates across genders, ages or regions.
• biasSystematic unfairness in a model's outputs, for example working worse for some groups of people, usually caused by skewed data or design choices.
• featureOne measurable piece of information given to a model as input, for example a customer's age, the number of past orders or the brightness of a pixel.
• alignmentMaking an AI system's behavior match human intentions and values, so that it is helpful and honest and avoids causing harm. Also the research field that studies this.

This word in other fields

The same English word can have a different meaning in another field:

• explainability · Software Engineering

More terms: Bias, Safety and Responsible AI

• guardrail
• red teaming
• jailbreak