相关论文: Handling and Presenting Harmful Text in NLP Resear…

The issue of hate speech extends beyond the confines of the online realm. It is a problem with real-life repercussions, prompting most nations to formulate legal frameworks that classify hate speech as a punishable offence. These legal…

Disclaimer: This paper is concerned with violent online harassment. To describe the subject at an adequate level of realism, examples of our collected tweets involve violent, threatening, vulgar and hateful speech language in the context of…

Language models (LMs) are pretrained on diverse data sources, including news, discussion forums, books, and online encyclopedias. A significant portion of this data includes opinions and perspectives which, on one hand, celebrate democracy…

Threat detection in Natural Language Processing lacks consistent definitions and standardized benchmarks, and is often conflated with broader phenomena such as toxicity, hate speech, or offensive language. In this work, we introduce…

Language can be used as a means of reproducing and enforcing harmful stereotypes and biases and has been analysed as such in numerous research. In this paper, we present a survey of 304 papers on gender bias in natural language processing.…

With the widespread availability of LLMs since the release of ChatGPT and increased public scrutiny, commercial model development appears to have focused their efforts on 'safety' training concerning legal liabilities at the expense of…

The fundamental problem in toxicity detection task lies in the fact that the toxicity is ill-defined. This causes us to rely on subjective and vague data in models' training, which results in non-robust and non-accurate results: garbage in…

This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…

Objective: This review aims to explore the potential and challenges of using Natural Language Processing (NLP) to detect, correct, and mitigate medically inaccurate information, including errors, misinformation, and hallucination. By…

In an effort to mitigate the harms of large language models (LLMs), learning from human feedback (LHF) has been used to steer LLMs towards outputs that are intended to be both less harmful and more helpful. Despite the widespread adoption…

Hate Speech takes many forms to target communities with derogatory comments, and takes humanity a step back in societal progress. HateXplain is a recently published and first dataset to use annotated spans in the form of rationales, along…

Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users. However, these techniques suffer from various…

An adversarial example is an input transformed by small perturbations that machine learning models consistently misclassify. While there are a number of methods proposed to generate adversarial examples for text data, it is not trivial to…

Textual adversarial samples play important roles in multiple subfields of NLP research, including security, evaluation, explainability, and data augmentation. However, most work mixes all these roles, obscuring the problem definitions and…

Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the overall efficiency and accuracy of content review. However,…

The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language…

Progress on many Natural Language Processing (NLP) tasks, such as text classification, is driven by objective, reproducible and scalable evaluation via publicly available benchmarks. However, these are not always representative of…

Current research on hate speech analysis is typically oriented towards monolingual and single classification tasks. In this paper, we present a new multilingual hate speech analysis dataset for English, Hindi, Arabic, French, German and…

Large language models (LLMs) are increasingly deployed in high-stakes domains, where rare but severe failures can result in irreversible harm. However, prevailing evaluation benchmarks often reduce complex social risk to mean-centered…

From a computer science perspective, addressing on-line hate speech is a challenging task that is attracting the attention of both industry (mainly social media platform owners) and academia. In this chapter, we provide an overview of…