“…Model-aware approaches [16], [17], [18], [19], [20], [21], [22], [23], [24], [25], [12], [26], on the other hand, take the internal structure of the model into account and therefore tend to yield more precise model based explanations. For example, LRP [2], a model-aware post-hoc XAI approach, has been widely used to explain the decisions of various deep neural networks, such as convolutional neural networks, recurrent neural networks and graph neural networks [27]. Because of its importance in general, and to this paper in particular, we briefly describe the basic idea of LRP.…”