Hate speech is one type of harmful online content which directly attacks or promotes hate
towards a group or an individual member based on their actual or perceived aspects of …

Data-driven and machine learning based approaches for detecting, categorising and
measuring abusive content such as hate speech and harassment have gained traction due …

We present a holistic approach to building a robust and useful natural language
classification system for real-world content moderation. The success of such a system relies …

We introduce Dynabench, an open-source platform for dynamic dataset creation and model
benchmarking. Dynabench runs in a web browser and supports human-and-model-in-the …

Abstract Language models can generate harmful and biased outputs and exhibit
undesirable behavior according to a given cultural context. We propose a Process for …

Detecting online hate is a difficult task that even state-of-the-art models struggle with.
Typically, hate speech detection models are evaluated by measuring their performance on …

We present a human-and-model-in-the-loop process for dynamically generating datasets
and training better performing and more robust hate detection models. We provide a new …

Without proper safeguards, large language models will readily follow malicious instructions
and generate toxic content. This risk motivates safety efforts such as red-teaming and large …

With the advent of the internet and numerous social media platforms, citizens now have
enormous opportunities to express and share their opinions on various societal and political …

The presence of offensive language on social media platforms and the implications this
poses is becoming a major concern in modern society. Given the enormous amount of …