Related papers: Mitigating Biases in Toxic Language Detection thro…

Robustness of machine learning models on ever-changing real-world data is critical, especially for applications affecting human well-being such as content moderation. New kinds of abusive language continually emerge in online discussions in…

Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data. We present a methodology for programmatically identifying and removing…

Hate speech classifiers exhibit substantial performance degradation when evaluated on datasets different from the source. This is due to learning spurious correlations between words that are not necessarily relevant to hateful language, and…

The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person.…

The proliferation of social media platforms has led to an increase in the spread of hate speech, particularly targeting vulnerable communities. Unfortunately, existing methods for automatically identifying and blocking toxic language rely…

Large Language Models (LLMs) are increasingly used for toxicity assessment in online moderation systems, where fairness across demographic groups is essential for equitable treatment. However, LLMs often produce inconsistent toxicity…

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes.…

Given the dynamic nature of toxic language use, automated methods for detecting toxic spans are likely to encounter distributional shift. To explore this phenomenon, we evaluate three approaches for detecting toxic spans under cross-domain…

The censorship of toxic comments is often left to the judgment of imperfect models. Perspective API, a creation of Google technology incubator Jigsaw, is perhaps the most widely used toxicity classifier in industry; the model is employed by…

Social network platforms are generally used to share positive, constructive, and insightful content. However, in recent times, people often get exposed to objectionable content like threat, identity attacks, hate speech, insults, obscene…

The opaque nature of deep learning models presents significant challenges for the ethical deployment of hate speech detection systems. To address this limitation, we introduce Supervised Rational Attention (SRA), a framework that explicitly…

The presence of toxic content has become a major problem for many online communities. Moderators try to limit this problem by implementing more and more refined comment filters, but toxic users are constantly finding new ways to circumvent…

Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed. In this work, we explore an alternative perspective by…

From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In this study we (i)…

We propose to learn invariant representations, in the data domain, to achieve interpretability in algorithmic fairness. Invariance implies a selectivity for high level, relevant correlations w.r.t. class label annotations, and a robustness…

While deep learning models are making fast progress on the task of Natural Language Inference, recent studies have also shown that these models achieve high accuracy by exploiting several dataset biases, and without deep understanding of…

The last few years have witnessed an exponential rise in the propagation of offensive text on social media. Identification of this text with high precision is crucial for the well-being of society. Most of the existing approaches tend to…

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…