Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for
machine translation (for example, COMET or BERTScore) are based on black-box large …

Saliency maps can explain a neural model's predictions by identifying important input
features. They are difficult to interpret for laypeople, especially for instances with many …

Different users of machine learning methods require different explanations, depending on
their goals. To make machine learning accountable to society, one important goal is to get …

The recent spike in certified Artificial Intelligence (AI) tools for healthcare has renewed the
debate around adoption of this technology. One thread of such debate concerns Explainable …

The human-centric explainable artificial intelligence (HCXAI) community has raised the
need for framing the explanation process as a conversation between human and machine …

Contrastive explanations, where one decision is explained in contrast to another, are
supposed to be closer to how humans explain a decision than non-contrastive explanations …

While recently developed NLP explainability methods let us open the black box in various
ways (Madsen et al., 2022), a missing ingredient in this endeavor is an interactive tool …

Artificial Intelligence (AI) systems are increasingly pervasive: Internet of Things, in-car
intelligent devices, robots, and virtual assistants, and their large-scale adoption makes it …

Interpretability tools that offer explanations in the form of a dialogue have demonstrated their
efficacy in enhancing users' understanding, as one-off explanations may occasionally fall …

Although AI systems have proved to be powerful in supporting decision making in critical
domains, the underlying complexity and their poor explainability pose great challenges for …