Related papers: Suum Cuique: Studying Bias in Taboo Detection with…

Technologies for abusive language detection are being developed and applied with little consideration of their potential biases. We examine racial bias in five different sets of Twitter data annotated for hate speech and abusive language.…

Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and…

The perceived toxicity of language can vary based on someone's identity and beliefs, but this variation is often ignored when collecting toxic language datasets, resulting in dataset and model biases. We seek to understand the who, why, and…

Social stereotypes negatively impact individuals' judgements about different groups and may have a critical role in how people understand language directed toward minority social groups. Here, we assess the role of social stereotypes in the…

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 manifest in false positives when these identifiers are present,…

While the impact of social biases in language models has been recognized, prior methods for bias evaluation have been limited to binary association tests on small datasets, limiting our understanding of bias complexities. This paper…

Text toxicity detection systems exhibit significant biases, producing disproportionate rates of false positives on samples mentioning demographic groups. But what about toxicity detection in speech? To investigate the extent to which…

Discriminatory language and biases are often present in hate speech during conversations, which usually lead to negative impacts on targeted groups such as those based on race, gender, and religion. To tackle this issue, we propose an…

Uses of pejorative expressions can be benign or actively empowering. When models for abuse detection misclassify these expressions as derogatory, they inadvertently censor productive conversations held by marginalized groups. One way to…

Recent research has demonstrated how racial biases against users who write African American English exists in popular toxic language datasets. While previous work has focused on a single fairness criteria, we propose to use additional…

Reference texts such as encyclopedias and news articles can manifest biased language when objective reporting is substituted by subjective writing. Existing methods to detect bias mostly rely on annotated data to train machine learning…

Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications. However, evidence of inherent bias encoded in these LLMs has…

Though majority vote among annotators is typically used for ground truth labels in natural language processing, annotator disagreement in tasks such as hate speech detection may reflect differences in opinion across groups, not noise. Thus,…

Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified…

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 and consumers of the posts play a crucial role in…

The prevalence and impact of toxic discussions online have made content moderation crucial.Automated systems can play a vital role in identifying toxicity, and reducing the reliance on human moderation.Nevertheless, identifying toxic…

With surge in online platforms, there has been an upsurge in the user engagement on these platforms via comments and reactions. A large portion of such textual comments are abusive, rude and offensive to the audience. With machine learning…

Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in…

We study Socially Unacceptable Discourse (SUD) characterization and detection in online text. We first build and present a novel corpus that contains a large variety of manually annotated texts from different online sources used so far in…

Since state-of-the-art approaches to offensive language detection rely on supervised learning, it is crucial to quickly adapt them to the continuously evolving scenario of social media. While several approaches have been proposed to tackle…