Provably Robust Model-Centric Explanations for Critical Decision-Making
This addresses the need for reliable explanations in high-stakes AI applications, offering a novel approach that is complementary to existing methods.
The paper tackles the problem of obtaining robust explanations for AI model behavior in critical decision-making by proposing a model-centric Boolean Satisfiability (SAT) formalism, which is shown to provide actionable insights and invariant explanations, contrasting with data-centric methods like LIME and SHAP that yield brittle explanations.
We recommend using a model-centric, Boolean Satisfiability (SAT) formalism to obtain useful explanations of trained model behavior, different and complementary to what can be gleaned from LIME and SHAP, popular data-centric explanation tools in Artificial Intelligence (AI). We compare and contrast these methods, and show that data-centric methods may yield brittle explanations of limited practical utility. The model-centric framework, however, can offer actionable insights into risks of using AI models in practice. For critical applications of AI, split-second decision making is best informed by robust explanations that are invariant to properties of data, the capability offered by model-centric frameworks.