-
Facial Recognition Technologies in the Wild
Facial Recognition Technologies in the Wild: A Call for a Federal Office -
Gender Shades
Gender Shades: Intersectional accuracy disparities in commercial gender classification -
ENTIGEN: Evaluating the Effect of Ethical Interventions on Text-to-Image Gene...
The ENTIGEN dataset is a benchmark for evaluating the change in the diversity of text-to-image generations in the presence of ethical interventions. -
Content Moderation Dataset (CMD)
A dataset of social media content containing potentially biased (unsafe) texts, along with unbiased (safe or benign) variations. -
Inducing Anxiety in Large Language Models Increases Exploration and Bias
The Inducing Anxiety in Large Language Models Increases Exploration and Bias dataset contains anxiety-inducing scenarios for large language models. -
News dataset
The dataset used in the paper is a semi-synthetic news dataset, which simulates a dynamic ranking problem on a set of news articles belonging to two groups (left-leaning and... -
Movie dataset
The Movie dataset is a graph dataset constructed from the Movielens-2k dataset. The Movielens-2k dataset contains movies information such as actors, genres, and tags... -
RealToxicityPrompts
RealToxicityPrompts constitutes a collection of 100k naturally occurring sentences, amassed from various internet sources and designed to function as LM prompts. -
Loan Approval Dataset
The dataset used in the paper is a simulation study for a loan approval case, measuring the financial impact of different choices on the worst-off group.
