ExSum: From Local Explanations to Model Understanding

TitleExSum: From Local Explanations to Model Understanding
Publication TypeConference Paper
Year of Publication2022
AuthorsZhou, Y., M. Tulio Ribeiro, and J. Shah
Conference NameAnnual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
Date Published07/2022
PublisherAssociation for Computational Linguistics
AbstractInterpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment. Fulfilling this goal requires both that the explanations generated by these methods are correct and that people can easily and reliably understand them. While the former has been addressed in prior work, the latter is often overlooked, resulting in informal model understanding derived from a handful of local explanations. In this paper, we introduce explanation summary (ExSum), a mathematical framework for quantifying model understanding, and propose metrics for its quality assessment. On two domains, ExSum highlights various limitations in the current practice, helps develop accurate model understanding, and reveals easily overlooked properties of the model. We also connect understandability to other properties of explanations such as human alignment, robustness, and counterfactual minimality and plausibility.