← Search

Benedict Clark

2 accepted papers

2025

Correcting misinterpretations of additive models

NeurIPS 2025poster

Correct model interpretation in high-stakes settings is critical, yet both post-hoc feature attribution methods and so-called intrinsically interpretable models can systematically attribute false-positive importance to non-informative features such as suppressor variables. Specifically, both linear…

Cited by 0SourceScholar
2023

Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables

ICML 2023poster

In recent years, the community of 'explainable artificial intelligence' (XAI) has created a vast body of methods to bridge a perceived gap between model 'complexity' and 'interpretability'. However, a concrete problem to be solved by XAI methods has not yet been formally stated. As a result, XAI met…

Cited by 12SourcePDFScholar