Social stereotypes negatively impact individuals' judgments about different groups and may
have a critical role in understanding language directed toward marginalized groups. Here …

The perceived toxicity of language can vary based on someone's identity and beliefs, but
this variation is often ignored when collecting toxic language datasets, resulting in dataset …

Abstract The quality of Machine Learning (ML) applications is commonly assessed by
quantifying how well an algorithm fits its respective training data. Yet, a perfect model that …

Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output
to biased and toxic generations. Due to several limiting factors surrounding LLMs (training …

The emergence of the transformer architecture has ushered in a new era of possibilities,
showcasing remarkable capabilities in generative tasks exemplified by models like GPT4o …

When training data are collected from human annotators, the design of the annotation
instrument, the instructions given to annotators, the characteristics of the annotators, and …

Human annotation plays a core role in machine learning--annotations for supervised
models, safety guardrails for generative models, and human feedback for reinforcement …

Detecting “toxic” language in internet content is a pressing social and technical challenge. In
this work, we focus on Perspective API from Jigsaw, a state-of-the-art tool that promises to …

Decisions about how to responsibly collect, use and document data often rely upon
understanding how people are represented in data. Yet, the unlabeled nature and scale of …

The speed and scale at which machine learning (ML) systems are deployed are
accelerating even as an increasing number of studies highlight their potential for negative …