Technological advancements over the years have led to increasingly complex software systems. The recent surge in artificial intelligence (AI) has, while reducing human effort, further contributed to this complexity. Among the growing concerns in this domain are the ethical implications of developing and using such systems. Regardless of whether a system explicitly incorporates AI, underlying software infrastructures have demonstrated instances of discriminatory behavior, resulting in undesired outcomes. To address this challenge, my research focuses on discrimination testing as a means to ensure equitable behavior in software systems. As part of this effort, I plan to build on insights from my earlier work, which involved compiling a list of existing tools and user studies on their effectiveness. My goal is to design a more explainable and generalizable discrimination testing tool that can be applied across various systems.

Fairness in AI models has become essential as our society increasingly becoming more dependent on AI. A biased model can have a harmful impact on marginalized communities. To address this issue, practitioners have developed fairness tools over time. To understand their practical implication, we designed an interview to curate experiences with fairness tools from academic practioners’. In this paper, we discuss insights from our first round of interviews with practitioners from academia. Although numerous fairness tools have been developed, only a few industry-developed (e.g., AIF360 and Fairlearn) are practically usable and commonly employed by practitioners due to regular maintenance & visibility. The existing toolkit landscape is primarily equipped to solely handle textual data and lacks sufficient resources for language models. Our findings thus far provide insights into one perspective on fairness tool engagement; our future efforts will investigate experiences and perspectives on fairness tool support beyond traditional models.

Biased machine learning (ML) models in real-world applications, such as healthcare and criminal justice, have led to significant societal harm. Several ML fairness tools promise to help create less biased ML models. However, little effort has been made to help practitioners or researchers reason about the growing space of available tools. In this work, we evaluated and categorized 14 existing fairness tools based on their features and usage workflows to develop a practical taxonomy of machine learning fairness tools. Our resulting taxonomy of fairness tools suggests the availability of an array of fairness tools, including tools that require little coding or allow for customization or extension. By structuring and organizing the landscape of fairness tools, we can identify gaps and explore options for supporting researchers and practitioners, such as automated tools for finding and selecting fairness tools.