Related papers: Beyond Accuracy: An Explainability-Driven Analysis…

Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges…

With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this…

Toxicity detection algorithms, originally designed with reactive content moderation in mind, are increasingly being deployed into proactive end-user interventions to moderate content. Through a socio-technical lens and focusing on contexts…

Content moderation typically combines the efforts of human moderators and machine learning models. However, these systems often rely on data where significant disagreement occurs during moderation, reflecting the subjective nature of…

Hate speech detection is a crucial area of research in natural language processing, essential for ensuring online community safety. However, detecting implicit hate speech, where harmful intent is conveyed in subtle or indirect ways,…

This paper presents a pipeline to detect and explain anomalous reviews in online platforms. The pipeline is made up of three modules and allows the detection of reviews that do not generate value for users due to either worthless or…

Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…

With growing role of social media in shaping public opinions and beliefs across the world, there has been an increased attention to identify and counter the problem of hate speech on social media. Hate speech on online spaces has serious…

Online users today are exposed to misleading and propagandistic news articles and media posts on a daily basis. To counter thus, a number of approaches have been designed aiming to achieve a healthier and safer online news and media…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Implicit hate speech has recently emerged as a critical challenge for social media platforms. While much of the research has traditionally focused on harmful speech in general, the need for generalizable techniques to detect veiled and…

Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework…

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

Despite the recent successes of transformer-based models in terms of effectiveness on a variety of tasks, their decisions often remain opaque to humans. Explanations are particularly important for tasks like offensive language or toxicity…

The vast majority of research on explainability focuses on post-explainability rather than explainable modeling. Namely, an explanation model is derived to explain a complex black box model built with the sole purpose of achieving the…

There has been a growing interest in model-agnostic methods that can make deep learning models more transparent and explainable to a user. Some researchers recently argued that for a machine to achieve a certain degree of human-level…

In this paper we investigate the explainability of transformer models and their plausibility for hate speech and counter speech detection. We compare representatives of four different explainability approaches, i.e., gradient-based,…

Well-annotated data is a prerequisite for good Natural Language Processing models. Too often, though, annotation decisions are governed by optimizing time or annotator agreement. We make a case for nuanced efforts in an interdisciplinary…

The recent enthusiasm for artificial intelligence (AI) is due principally to advances in deep learning. Deep learning methods are remarkably accurate, but also opaque, which limits their potential use in safety-critical applications. To…

Computational social science research has made advances in machine learning and natural language processing that support content moderators in detecting harmful content. These advances often rely on training datasets annotated by…