Statistics and explainability: a fruitful alliance
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, and it can be achieved in this framework through classical statistical procedures such as the bootstrap. However, it is crucial to note that while Statistics offers valuable contributions, it is not a panacea for resolving all the challenges. Future research avenues could focus on open problems, such as defining a purpose for the explanations or establishing a statistical framework for counterfactual or adversarial scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualUncertainty QuantificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Alliances and Conflict, or Conflict and Alliances? Appraising the Causal Effect of Alliances on Conflict
The deterrent effect of military alliances is well documented and widely accepted. However, such work has typically assumed that alliances are exogenous. This is problematic as alliances may simultaneously influence the …
An Integrated Framework for Team Formation and Winner Prediction in the FIRST Robotics Competition: Model, Algorithm, and Analysis
This research work aims to develop an analytical approach for optimizing team formation and predicting team performance in a competitive environment based on data on the competitors' skills prior to the team formation. T…
Working Alliance Transformer for Psychotherapy Dialogue Classification
As a predictive measure of the treatment outcome in psychotherapy, the working alliance measures the agreement of the patient and the therapist in terms of their bond, task and goal. Long been a clinical quantity estimat…
ClassificationOn Structural Parameterizations of the Offensive Alliance Problem
The Offensive Alliance problem has been studied extensively during the last twenty years. A set $S\subseteq V$ of vertices is an offensive alliance in an undirected graph $G=(V,E)$ if each $v\in N(S)$ has at least as man…
The "given data" paradigm undermines both cultures
Breiman organizes "Statistical modeling: The two cultures" around a simple visual. Data, to the far right, are compelled into a "black box" with an arrow and then catapulted left by a second arrow, having been transforme…