Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model's decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.

翻译：事后解释方法是有助于理解经过培训的模型决定所依据的理由的一个重要方法类别。 但是,这些方法对于最终用户完成某项任务有多么有用?在本愿景文件中,我们主张需要制定基准,以便利评估受热后解释方法的效用。作为实现这一目标的第一步,我们列举了这一基准对于调试文本分类员的任务所应具备的可取属性。此外,我们强调,这种基准不仅有利于评估解释的有效性,而且有利于评估其效率。