we submitted a workshop paper "ModelSpeX: Model Specification Using Explainable Artificial Intelligence Methods" to the MLVis 2020 Workshop. We request to acknowledge SPARTA if the paper is accepted.

Explainable artificial intelligence (XAI) methods aim to reveal the non-transparent decision-making mechanisms of black-box models (e.g., deep learning models). The evaluation of insight generated by such XAI methods remains challenging as the applied techniques depend on many factors (e.g., parameters, human interpretation). We propose ModelSpeX, a visual analytics workflow to interactively extract human-centered rule-sets to generate model specifications from black-box models. The workflow enables to reason about the underlying problem, to extract rule sets, and to evaluate the suitability of the models for a particular task. An exemplary usage scenario walks an analyst trough the steps of the workflow to show the applicability.