Abstract Machine learning (ML) systems in natural language processing (NLP) face
significant challenges in generalizing to out-of-distribution (OOD) data, where the test …

Text-based explanation is a particularly promising approach in explainable AI, but the
evaluation of text explanations is method-dependent. We argue that placing the …

As large and powerful neural language models are developed, researchers have been
increasingly interested in developing diagnostic tools to probe them. There are many papers …

In recent years, the impressive abilities shown by deep neural network (DNN)-based
systems have led to the curiosity towards the intrinsic mechanisms. The query towards these …