Towards Responsible AI: A Design Space Exploration of Human-Centered Artificial Intelligence User Interfaces to Investigate Fairness

TL;DR

This paper explores a design space for human-centered AI user interfaces focused on fairness, introducing FairHIL, a UI supporting human-in-the-loop fairness assessments, evaluated through user studies to advance responsible AI practices.

Contribution

It presents a novel UI, FairHIL, enabling both data scientists and domain experts to investigate AI fairness, based on requirements elicited from real-world stakeholders.

Findings

FairHIL supports human-in-the-loop fairness investigations.

Workshops effectively elicited stakeholder requirements.

User study shows improved fairness analysis capabilities.

Abstract

With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI) design, recent efforts have produced user interfaces (UIs) for AI experts to investigate the fairness of AI models. In this work, we provide a design space exploration that supports not only data scientists but also domain experts to investigate AI fairness. Using loan applications as an example, we held a series of workshops with loan officers and data scientists to elicit their requirements. We instantiated these requirements into FairHIL, a UI to support human-in-the-loop fairness investigations, and describe how this UI could be generalized to other use cases. We evaluated FairHIL through a think-aloud user study. Our work contributes better designs to investigate an AI model's fairness-and move closer towards responsible AI.