Statistics and explainability: a fruitful alliance

arXiv:2404.19301v1 Announce Type: cross
Abstract: In this paper, we propose standard statistical tools as a solution to commonly highlighted problems in the explainability literature. Indeed, leveraging statistical estimators allows for a proper definition of explanations, enabling theoretical guarantees and the formulation of evaluation metrics to quantitatively assess the quality of explanations. This approach circumvents, among other things, the subjective human assessment currently prevalent in the literature. Moreover, we argue that uncertainty quantification is essential for providing robust and trustworthy explanations, …

abstract arxiv cs.lg definition enabling evaluation evaluation metrics explainability indeed literature metrics paper quality solution standard statistical statistics stat.ml tools type