Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment
This work addresses the need for effective explanations to support human fairness judgments in ML, though it is incremental as it builds on existing explanation methods.
The study investigated how four types of programmatically generated explanations affect people's fairness judgments of ML systems, finding that certain explanations are seen as less fair while others boost confidence, and that different explanation styles better expose various fairness issues.
Ensuring fairness of machine learning systems is a human-in-the-loop process. It relies on developers, users, and the general public to identify fairness problems and make improvements. To facilitate the process we need effective, unbiased, and user-friendly explanations that people can confidently rely on. Towards that end, we conducted an empirical study with four types of programmatically generated explanations to understand how they impact people's fairness judgments of ML systems. With an experiment involving more than 160 Mechanical Turk workers, we show that: 1) Certain explanations are considered inherently less fair, while others can enhance people's confidence in the fairness of the algorithm; 2) Different fairness problems--such as model-wide fairness issues versus case-specific fairness discrepancies--may be more effectively exposed through different styles of explanation; 3) Individual differences, including prior positions and judgment criteria of algorithmic fairness, impact how people react to different styles of explanation. We conclude with a discussion on providing personalized and adaptive explanations to support fairness judgments of ML systems.