Provably Robust Model-Centric Explanations for Critical Decision-Making
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 15 references that are in the map. First posted on arXiv 26 Oct 2021.
Builds on
5 of 15 references.
References · 5
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2017Interpretation of Neural Networks is Fragilecited by 444
- 2018On the Robustness of Interpretability Methodscited by 314
- 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
Built on by
Not cited yet.