The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …

Hate speech is one type of harmful online content which directly attacks or promotes hate
towards a group or an individual member based on their actual or perceived aspects of …

Graph neural networks (GNNs) have become a popular approach to integrating structural
inductive biases into NLP models. However, there has been little work on interpreting them …

Pre-trained language models (PLMs) are known to improve the generalization performance
of natural language understanding models by leveraging large amounts of data during the …

The great success of Transformer-based models benefits from the powerful multi-head self-
attention mechanism, which learns token dependencies and encodes contextual information …

Detecting online toxicity has always been a challenge due to its inherent subjectivity. Factors
such as the context, geography, socio-political climate, and background of the producers …

Hate speech classifiers trained on imbalanced datasets struggle to determine if group
identifiers like" gay" or" black" are used in offensive or prejudiced ways. Such biases …

Reducing and counter-acting hate speech on Social Media is a significant concern. Most of
the proposed automatic methods are conducted exclusively on English and very few …

Transformer-based neural networks offer very good classification performance across a
wide range of domains, but do not provide explanations of their predictions. While several …

Natural Language Processing (NLP) models risk overfitting to specific terms in the training
data, thereby reducing their performance, fairness, and generalizability. Eg, neural hate …