Which techniques help make AI decisions understandable to humans?

Which techniques help make AI decisions understandable to humans?

• A. Explainable AI (XAI)
• B. Data privacy issues
• C. Generative AI
• D. Hybrid approaches

Answer: (A)

Explainable AI is about making AI decisions understandable to humans. It focuses on providing explanations for predictions, showing how inputs contribute to outcomes, and enabling trust, auditing, and debugging. Techniques include inherently interpretable models and post-hoc methods like feature importance, SHAP values, and LIME, which reveal how different features push a decision in a given direction. This clarity is especially important in high-stakes domains. The other options don’t center on making decisions interpretable: data privacy concerns protect information, generative AI creates new content, and hybrid approaches refer to combining methods rather than explaining decisions.

Explainable AI is about making AI decisions understandable to humans. It focuses on providing explanations for predictions, showing how inputs contribute to outcomes, and enabling trust, auditing, and debugging. Techniques include inherently interpretable models and post-hoc methods like feature importance, SHAP values, and LIME, which reveal how different features push a decision in a given direction. This clarity is especially important in high-stakes domains. The other options don’t center on making decisions interpretable: data privacy concerns protect information, generative AI creates new content, and hybrid approaches refer to combining methods rather than explaining decisions.