Explaining models: an empirical study of how explanations impact fairness judgment
By Jonathan Dodge, Q. Liao, Yunfeng Zhang, Rachel K. E. Bellamy, Casey Dugan. 2019
162 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Safety Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Safety Research
Citations in the corpus
- In AI We Trust? Factors That Influence Trustworthiness of AI-infused Decision-Making Processes (2019, background): “not trustworthy, similar to Dodge et al’s study of how explanations impact peoples’ judgments of the fairness of an AI algorithm [9].”
- Counterfactual Explanations for Machine Learning: A Review (2020, unknown): “[32] performed user-studies which showed”