Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.16255 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908333219250176 |
|---|---|
| author | Behzad, Tina Singh, Mithilesh Kumar Ripa, Anthony J. Mueller, Klaus |
| author_facet | Behzad, Tina Singh, Mithilesh Kumar Ripa, Anthony J. Mueller, Klaus |
| contents | 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 of perspectives 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. In the absence of such a tool, reaching a consensus would be highly challenging due to the lack of a systematic negotiation process and the inability to modify and observe changes. We have conducted user studies that demonstrate the success of FairPlay, as users could reach a consensus within about five rounds of gameplay, illustrating the application's potential for enhancing fairness in AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16255 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness Behzad, Tina Singh, Mithilesh Kumar Ripa, Anthony J. Mueller, Klaus Machine Learning Computers and Society Human-Computer Interaction H.5.2; H.5.3; I.2.6 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 of perspectives 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. In the absence of such a tool, reaching a consensus would be highly challenging due to the lack of a systematic negotiation process and the inability to modify and observe changes. We have conducted user studies that demonstrate the success of FairPlay, as users could reach a consensus within about five rounds of gameplay, illustrating the application's potential for enhancing fairness in AI systems. |
| title | FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness |
| topic | Machine Learning Computers and Society Human-Computer Interaction H.5.2; H.5.3; I.2.6 |
| url | https://arxiv.org/abs/2504.16255 |