"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset

Understand

As language models grow in popularity, it becomes increasingly important to clearly measure all possible markers of demographic identity in order to avoid perpetuating existing societal harms.

• Many datasets for measuring bias currently exist, but they are restricted in their coverage of demographic axes and are commonly used with preset bias tests that presuppose which types of biases models can exhibit.
• In this work, we present a new, more inclusive bias measurement dataset, HolisticBias, which includes nearly 600 descriptor terms across 13 different demographic axes.
• HolisticBias was assembled in a participatory process including experts and community members with lived experience of these terms.