Related papers: When Does Demographic Information Help? Data and M…

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…

Some users of social media are spreading racist, sexist, and otherwise hateful content. For the purpose of training a hate speech detection system, the reliability of the annotations is crucial, but there is no universally agreed-upon…

Language models have been shown to propagate social bias through their output, particularly in the representation of gender and ethnicity. This paper investigates gender and ethnicity biases in AI-generated occupational stories.…

Researchers have raised awareness about the harms of aggregating labels especially in subjective tasks that naturally contain disagreements among human annotators. In this work we show that models that are only provided aggregated labels…

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.…

Data augmentation is widely used in vision to introduce variation and mitigate overfitting, by enabling models to learn invariant properties. However, augmentation only indirectly captures these properties and does not explicitly constrain…

Hate speech detection has been the subject of high research attention, due to the scale of content created on social media. In spite of the attention and the sensitive nature of the task, privacy preservation in hate speech detection has…

Crowdsourced annotation is vital to both collecting labelled data to train and test automated content moderation systems and to support human-in-the-loop review of system decisions. However, annotation tasks such as judging hate speech are…

We identify and explore differential access to population-level signaling (also known as information design) as a source of unequal access to opportunity. A population-level signaler has potentially noisy observations of a binary type for…

Despite the widespread adoption, there is a lack of research into how various critical aspects of pretrained language models (PLMs) affect their performance in hate speech detection. Through five research questions, our findings and…

Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning of enriched features. This raises the question of whether…

We investigate how independent demographic bias mechanisms are from general demographic recognition in language models. Using a multi-task evaluation setup where demographics are associated with names, professions, and education levels, we…

Instead of using a single ground truth for language processing tasks, several recent studies have examined how to represent and predict the labels of the set of annotators. However, often little or no information about annotators is known,…

In attempts to develop sample-efficient and interpretable algorithms, researcher have explored myriad mechanisms for collecting and exploiting feature feedback (or rationales) auxiliary annotations provided for training (but not test)…

Bias mitigation approaches reduce models' dependence on sensitive features of data, such as social group tokens (SGTs), resulting in equal predictions across the sensitive features. In hate speech detection, however, equalizing model…

Demographic cue-based evaluation is widely used to study how large language models (LLMs) adapt their responses to signaled demographic attributes within and across groups. This approach typically relies on a single cue (e.g., names) as a…

Fine resolution estimates of demographic and socioeconomic attributes are crucial for planning and policy development. While several efforts have been made to produce fine-scale gridded population estimates, socioeconomic features are…

We present an approach to modeling annotator disagreement in subjective NLP tasks through both architectural and data-centric innovations. Our model, DEM-MoE (Demographic-Aware Mixture of Experts), routes inputs to expert subnetworks based…

A growing body of work has focused on text classification methods for detecting the increasing amount of hate speech posted online. This progress has been limited to only a select number of highly-resourced languages causing detection…

How should one combine noisy information from diverse sources to make an inference about an objective ground truth? This frequently recurring, normative question lies at the core of statistics, machine learning, policy-making, and everyday…