EARN Fairness: Explaining, Asking, Reviewing and Negotiating Artificial Intelligence Fairness Metrics Among Stakeholders

2024-07-16

arXiv.org

AI Summary

Non-technical stakeholders face significant barriers in defining and selecting fairness metrics for AI systems, hindering meaningful participation in high-stakes AI governance. Method: We propose EARN—a four-stage human-AI co-design framework (Explain–Ask–Reason–Negotiate)—to enable non-expert users to understand fairness metrics, articulate individual preferences, engage in collective deliberation, and reach consensus. Through participatory workshops, qualitative coding, and consensus modeling in a credit assessment context, we analyzed preference elicitation and consensus formation among 18 non-expert participants. Contribution/Results: EARN is the first framework to support cross-background stakeholders in autonomously and structurally negotiating fairness measurements for high-risk AI applications. It advances human-centered AI fairness practice by providing a reusable methodological foundation and system design paradigm grounded in participatory, deliberative, and consensus-oriented principles.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Game Theory and Economic Paradigms: Fair Division

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Numerous fairness metrics have been proposed and employed by artificial intelligence (AI) experts to quantitatively measure bias and define fairness in AI models. Recognizing the need to accommodate stakeholders' diverse fairness understandings, efforts are underway to solicit their input. However, conveying AI fairness metrics to stakeholders without AI expertise, capturing their personal preferences, and seeking a collective consensus remain challenging and underexplored. To bridge this gap, we propose a new framework, EARN Fairness, which facilitates collective metric decisions among stakeholders without requiring AI expertise. The framework features an adaptable interactive system and a stakeholder-centered EARN Fairness process to Explain fairness metrics, Ask stakeholders' personal metric preferences, Review metrics collectively, and Negotiate a consensus on metric selection. To gather empirical results, we applied the framework to a credit rating scenario and conducted a user study involving 18 decision subjects without AI knowledge. We identify their personal metric preferences and their acceptable level of unfairness in individual sessions. Subsequently, we uncovered how they reached metric consensus in team sessions. Our work shows that the EARN Fairness framework enables stakeholders to express personal preferences and reach consensus, providing practical guidance for implementing human-centered AI fairness in high-risk contexts. Through this approach, we aim to harmonize fairness expectations of diverse stakeholders, fostering more equitable and inclusive AI fairness.

Problem

• Facilitates collective fairness metric decisions
• Captures stakeholders' personal fairness preferences
• Enables consensus on AI fairness metrics

Innovation

• Interactive system for fairness
• Stakeholder-centered EARN process
• Empirical study on consensus