AI Transparency & Explainability: Manager’s Guide | QuizBy Eyal Doron / December 6, 2025 / 1 minute of reading AI Transparency & Explainability: Manager’s Guide | Quiz 1 / 7 1. Your organization is implementing AI explainability. What is the FIRST step in the implementation framework? 1. Training all staff on explainability concepts 2. Purchasing LIME and SHAP software licenses 3. Documenting all existing model architectures 4. Risk assessment to classify AI applications by explanation requirements Correct! WHY: Risk assessment must come first to classify AI applications by explanation requirements before selecting techniques. CONTEXT: High-stakes decisions need rigorous explanation capability while lower-stakes applications may need less. REMEMBER: Start with risk assessment – know your stakes before choosing your approach. 2 / 7 2. Why is attention visualization for LLMs considered limited as an explanation technique? 1. Attention patterns cannot be visualized in real-time 2. Attention mechanisms are not present in modern transformer models 3. Attention shows correlation not causation – high attention does not mean that input caused the output 4. Attention visualization only works for small language models Correct! WHY: Attention patterns show correlation not causation – high attention on an input does not necessarily mean that input caused the output. CONTEXT: This limitation means attention visualization should be used carefully not as definitive proof of model reasoning. REMEMBER: Attention shows what the model looked at not why it made a decision. 3 / 7 3. What is the Two-Model Approach to balancing accuracy and explainability? 1. Use one model during development and another during production 2. Use a high-performance model for predictions and a simpler model to generate explanations 3. Train two identical models and compare their outputs for consistency 4. Deploy two models in different regions to meet local regulations Correct! WHY: The Two-Model Approach uses a high-performance model for predictions and a simpler interpretable model to generate explanations. CONTEXT: This provides both accuracy and transparency without sacrificing either. REMEMBER: Two-Model Approach equals one model for accuracy plus one model for explanations. 4 / 7 4. According to the EU AI Act what level of transparency is required for high-risk AI systems? 1. No transparency requirements for AI systems 2. Full source code publication 3. Basic disclosure of the model type only 4. Extensive documentation and explanation capability Correct! WHY: The EU AI Act requires extensive documentation and explanation capability for high-risk AI systems. CONTEXT: Requirements scale with risk level and providers must ensure systems can be understood by operators. REMEMBER: EU AI Act equals risk-scaled transparency – higher risk equals more documentation and explanation capability. 5 / 7 5. What is a counterfactual explanation? 1. An explanation that predicts what the model would have decided in the past 2. An explanation that shows all factors that did not influence the decision 3. An explanation that shows what would need to change for a different outcome 4. An explanation that compares the current model to a previous version Correct! WHY: Counterfactual explanations answer what would need to change for a different outcome making them actionable for users. CONTEXT: Users often find counterfactuals more useful than feature importance because they know what to do differently. REMEMBER: Counterfactuals explain by showing what you could change to get a different result. 6 / 7 6. What does SHAP use to determine feature importance in AI predictions? 1. Random sampling of input features 2. Game theory concepts specifically Shapley values 3. Decision tree node splits 4. Neural network attention patterns Correct! WHY: SHAP uses game theory concepts specifically Shapley values to assign importance to each feature for a prediction. CONTEXT: SHAP provides theoretically grounded and consistent feature importance making it a popular choice for explaining black box models. REMEMBER: SHAP equals Shapley values equals game theory for feature importance. 7 / 7 7. Which regulation grants individuals the right to meaningful information about the logic involved in automated decisions? 1. NYC Local Law 144 2. GDPR Article 22 3. SOC 2 Type II 4. EU AI Act Article 1 Correct! WHY: GDPR Article 22 specifically addresses automated decision-making and requires organizations to provide meaningful information about the logic involved. CONTEXT: This right applies when AI makes decisions about credit employment insurance or similar consequential outcomes. REMEMBER: GDPR Article 22 is your right to explanation for automated decisions. Your score isThe average score is 0% Restart quiz Download PDF Please leave this field emptyš The AI Security Manager's Newsletter Weekly insights on AI risk management, EU AI Act compliance, and practical security strategies. We donāt spam! Read our privacy policy for more info. Thank you! Please check your inbox to confirm your subscription.
