FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness
Abstract
The issue of fairness in decision-making is a critical one, especially given the variety of stakeholder demands for differing and mutually incompatible versions of fairness. Adopting a strategic interaction perspective provides an alternative to enforcing a singular standard of fairness. We present a web-based software application, FairPlay, that enables multiple stakeholders to debias datasets collaboratively. With FairPlay, users can negotiate and arrive at a mutually acceptable outcome without a universally agreed-upon theory of fairness. We have conducted user studies that demonstrate the success of FairPlay, with users reaching consensus within about five rounds of gameplay, illustrating the application’s potential for enhancing fairness in AI systems.
Cite
Text
Behzad et al. "FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness." NeurIPS 2024 Workshops: Pluralistic-Alignment, 2024.Markdown
[Behzad et al. "FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness." NeurIPS 2024 Workshops: Pluralistic-Alignment, 2024.](https://mlanthology.org/neuripsw/2024/behzad2024neuripsw-fairplay/)BibTeX
@inproceedings{behzad2024neuripsw-fairplay,
title = {{FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness}},
author = {Behzad, Tina and Singh, Mithilesh Kumar and Ripa, Anthony J. and Mueller, Klaus},
booktitle = {NeurIPS 2024 Workshops: Pluralistic-Alignment},
year = {2024},
url = {https://mlanthology.org/neuripsw/2024/behzad2024neuripsw-fairplay/}
}