Summary of Earn Fairness: Explaining, Asking, Reviewing, and Negotiating Artificial Intelligence Fairness Metrics Among Stakeholders, by Lin Luo et al.
EARN Fairness: Explaining, Asking, Reviewing, and Negotiating Artificial Intelligence Fairness Metrics Among Stakeholders
by Lin Luo, Yuri Nakao, Mathieu Chollet, Hiroya Inakoshi, Simone Stumpf
First submitted to arxiv on: 16 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed EARN Fairness framework aims to facilitate collective decisions on AI fairness metrics among stakeholders without requiring AI expertise. The framework features an interactive system that explains fairness metrics, asks for personal preferences, reviews metrics collectively, and negotiates a consensus on metric selection. A user study involving 18 decision subjects without AI knowledge was conducted to gather empirical results, which showed that the framework enables stakeholders to express personal preferences and reach consensus. This approach provides practical guidance for implementing human-centered AI fairness in high-risk contexts. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AI experts are trying to make sure AI systems are fair by using special metrics. But it’s hard to explain these metrics to people who don’t know about AI, and get them to agree on what’s fair. To solve this problem, a new framework called EARN Fairness was created. It helps groups of people work together to decide which fairness metrics to use without needing to understand AI technology. The framework includes steps like explaining the metrics, asking for personal preferences, and negotiating a consensus. A study was done with 18 people who didn’t know about AI to see how well this works. |
