Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI

1 code implementation • 3 Apr 2022 • Mahima Pushkarna, Andrew Zaldivar, Oddur Kjartansson

In this paper, we propose Data Cards for fostering transparent, purposeful and human-centered documentation of datasets within the practical contexts of industry and research.

Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias

no code implementations • 14 Jun 2019 • Emily Denton, Ben Hutchinson, Margaret Mitchell, Timnit Gebru, Andrew Zaldivar

Facial analysis models are increasingly used in applications that have serious impacts on people's lives, ranging from authentication to surveillance tracking.

Attribute counterfactual +1

Model Cards for Model Reporting

12 code implementations • 5 Oct 2018 • Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, Timnit Gebru

Model cards also disclose the context in which models are intended to be used, details of the performance evaluation procedures, and other relevant information.

BIG-bench Machine Learning