Cybertrust: From Explainable to Actionable and Interpretable AI (AI2)
This addresses the problem of trust in AI for users and operators, proposing a shift from explainable to actionable and interpretable AI, which is an incremental conceptual advancement.
The paper argues that AI systems should be designed to build trust through interpretable and actionable features, rather than focusing on explainability, by incorporating user confidence quantifications and visualizations to enable testing and establish trust in decision-making.
To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some understanding of AI operations can support predictability, but forcing AI to explain itself risks constraining AI capabilities to only those reconcilable with human cognition. We argue that AI systems should be designed with features that build trust by bringing decision-analytic perspectives and formal tools into AI. Instead of trying to achieve explainable AI, we should develop interpretable and actionable AI. Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. In doing so, it will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making and ensure broad benefits from deploying and advancing its computational capabilities.