Towards involving end-users in interactive human-in-the-loop AI fairness

Nakao, Y., Stumpf, S. , Ahmed, S., Naseer, A. and Strappelli, L. (2022) Towards involving end-users in interactive human-in-the-loop AI fairness. ACM Transactions on Intelligent Interactive Systems, 12(3), 18. (doi: 10.1145/3514258)

[img] Text
269192.pdf - Accepted Version

2MB

Abstract

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 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.

Item Type:Articles
Keywords:AI fairness, loan application decisions, end-users, human-in-the-loop, explanatory debugging, cultural dimensions.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Stumpf, Dr Simone
Authors: Nakao, Y., Stumpf, S., Ahmed, S., Naseer, A., and Strappelli, L.
Subjects:Q Science > Q Science (General)
T Technology > T Technology (General)
College/School:College of Science and Engineering > School of Computing Science
Journal Name:ACM Transactions on Intelligent Interactive Systems
Journal Abbr.:TiiS
Publisher:ACM
ISSN:2160-6455
ISSN (Online):2160-6463
Published Online:27 April 2022
Copyright Holders:Copyright © 2022 The Authors
First Published:First published in ACM Transactions on Intelligent Interactive Systems 12(3): 18
Publisher Policy:Reproduced in accordance with the publisher copyright policy

University Staff: Request a correction | Enlighten Editors: Update this record