Abstract Language models learn a great quantity of factual information during pretraining,
and recent work localizes this information to specific model weights like mid-layer MLP …

Attribution methods are a popular class of explainability methods that use heatmaps to
depict the most important areas of an image that drive a model decision. Nevertheless …

Deep neural networks (DNNs) have found their way into many applications with potential
impact on the safety, security, and fairness of human-machine-systems. Such require basic …

Humans usually explain their reasoning (eg classification) by dissecting the image and
pointing out the evidence from these parts to the concepts in their minds. Inspired by this …

We observe that the mapping between an image's representation in one model to its
representation in another can be learned surprisingly well with just a linear layer, even …

In recent years, concept-based approaches have emerged as some of the most promising
explainability methods to help us interpret the decisions of Artificial Neural Networks (ANNs) …

Abstract Concept Bottleneck Models (CBMs) have recently been proposed to address the
'black-box'problem of deep neural networks, by first mapping images to a human …

Modern deep learning methods have long been considered black boxes due to the lack of
insights into their decision-making process. However, recent advances in explainable …

Abstract Generalized Additive Models (GAMs) have quickly become the leading choice for
interpretable machine learning. However, unlike uninterpretable methods such as DNNs …

Explainable AI aims to overcome the black-box nature of complex ML models like neural
networks by generating explanations for their predictions. Explanations often take the form of …