Causality-Aware Local Interpretable Model-Agnostic Explanations

arXiv:2212.05256v3 Announce Type: replace-cross
Abstract: A main drawback of eXplainable Artificial Intelligence (XAI) approaches is the feature independence assumption, hindering the study of potential variable dependencies. This leads to approximating black box behaviors by analyzing the effects on randomly generated feature values that may rarely occur in the original samples. This paper addresses this issue by integrating causal knowledge in an XAI method to enhance transparency and enable users to assess the quality of the generated explanations. Specifically, we propose …

abstract artificial artificial intelligence arxiv black box box causality cs.ai cs.lg dependencies effects explainable artificial intelligence feature generated intelligence issue leads model-agnostic paper samples study type values xai