Interpretability and explainability have gained more and more attention in the field of machine learning as they are crucial when it comes to high-stakes decisions and troubleshooting. Since both provide information about predictors and their decision process, they are often seen as two independent means for one single end. This view has led to a dichotomous literature: explainability techniques designed for complex black-box models, or interpretable approaches ignoring the many explainability tools. In this position paper, we challenge the common idea that interpretability and explainability are substitutes for one another by listing their principal shortcomings and discussing how both of them mitigate the drawbacks of the other. In doing so, we call for a new perspective on interpretability and explainability, and works targeting both topics simultaneously, leveraging each of their respective assets.

翻译：可解释性与可理解性在机器学习领域受到越来越多的关注，因为它们在涉及高风险决策与故障排查时至关重要。由于两者均提供关于预测器及其决策过程的信息，它们常被视为实现同一目标的两种独立手段。这种观点导致文献呈现两极化：或为复杂黑箱模型设计可解释性技术，或采用可理解性方法却忽略众多可解释性工具。在本立场论文中，我们通过列举可解释性与可理解性的主要缺陷，并探讨二者如何相互弥补对方的不足，挑战了二者互为替代品的普遍认知。由此，我们呼吁对可解释性与可理解性建立新视角，并倡导同时关注这两大主题的研究工作，以充分发挥各自优势。