Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems

要旨

Representation bias is one of the most common types of biases in artificial intelligence (AI) systems, causing AI models to perform poorly on underrepresented data segments. Although AI practitioners use various methods to reduce representation bias, their effectiveness is often constrained by insufficient domain knowledge in the debiasing process. To address this gap, this paper introduces a set of generic design guidelines for effectively involving domain experts in representation debiasing. We instantiated our proposed guidelines in a healthcare-focused application and evaluated them through a comprehensive mixed-methods user study with 35 healthcare experts. Our findings show that involving domain experts can reduce representation bias without compromising model accuracy. Based on our findings, we also offer recommendations for developers to build robust debiasing systems guided by our generic design guidelines, ensuring more effective inclusion of domain experts in the debiasing process.

受賞
Honorable Mention
著者
Aditya Bhattacharya
KU Leuven, Leuven, Vlaams-Brabant, Belgium
Simone Stumpf
University of Glasgow, Glasgow, United Kingdom
Robin De Croon
KU Leuven, Leuven, Vlaams-Brabant, Belgium
Katrien Verbert
KU Leuven, Leuven, Belgium
DOI

10.1145/3706598.3713497

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713497

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: Using AI or Not

G314+G315
7 件の発表
2025-04-29 01:20:00
2025-04-29 02:50:00
日本語まとめ
読み込み中…