Towards Involving End-users in Interactive Human-in-the-loop AI Fairness
This work addresses the challenge of involving ordinary users in AI fairness decisions, which is an incremental step in human-computer interaction for fairness.
The paper tackled the problem of enabling non-expert end-users to identify and fix fairness issues in AI systems, specifically for loan decisions, by designing an interactive human-in-the-loop interface based on explanatory debugging, and evaluated it through workshops and an online study, though no concrete numerical results are provided.
Ensuring fairness in artificial intelligence (AI) is important to counteract bias and discrimination in far-reaching applications. Recent work has started to investigate how humans judge fairness and how to support machine learning (ML) experts in making their AI models fairer. Drawing inspiration from an Explainable AI (XAI) approach called \emph{explanatory debugging} used in interactive machine learning, our work explores designing interpretable and interactive human-in-the-loop interfaces that allow ordinary end-users without any technical or domain background to identify potential fairness issues and possibly fix them in the context of loan decisions. Through workshops with end-users, we co-designed and implemented a prototype system that allowed end-users to see why predictions were made, and then to change weights on features to "debug" fairness issues. We evaluated the use of this prototype system through an online study. To investigate the implications of diverse human values about fairness around the globe, we also explored how cultural dimensions might play a role in using this prototype. Our results contribute to the design of interfaces to allow end-users to be involved in judging and addressing AI fairness through a human-in-the-loop approach.