ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science

• Main Authors: Wolfe, Robert, Hiniker, Alexis, Howe, Bill
• Format: Journal Article
• Language: English
• Published: 04.08.2024
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Computation and Language; Computer Science - Computers and Society

This research introduces the Multilevel Embedding Association Test (ML-EAT), a method designed for interpretable and transparent measurement of intrinsic bias in language technologies. The ML-EAT addresses issues of ambiguity and difficulty in interpreting the traditional EAT measurement by quantify...