Table 5.

Association between XAI properties and explanation effectiveness measures.

Essential properties of XAI		Measures of explanation effectiveness
		Mental model	User satisfaction	Trust assessment	Task performance	Correctability
Stakeholders of XAI	AI regulators
	AI developers
	AI managers
	AI users		[29] [30] [31] [32] [33]	[32]	[31] [32] [33]	[30] [32] [34]
	Individuals affected by AI-based decisions		[29]	[29]
Objectives of XAI	Explainability to evaluate AI					[30] [32] [34]
	Explainability to justify AI			[29] [32]
	Explainability to improve AI		[29] [30] [31] [32] [34]		[31] [32] [33]
	Explainability to learn from AI
	Explainability to manage AI
Quality of personalized explanations	Fidelity				[33]	[30] [32] [34]
	Generalizability	N/A	N/A	N/A	N/A	N/A
	Explanatory power
	Interpretability
	Comprehensibility				[33]
	Plausibility		[29] [30] [31] [32] [34]	[29] [32]	[32]
	Effort				[31]
	Privacy
	Fairness