Inclusive Design of AI's Explanations: Just for Those Previously Left Out, or for Everyone?

TL;DR

This study investigates how inclusive design improvements to AI explanations can benefit all users, revealing increased engagement and understanding but also potential drawbacks like reduced prediction accuracy, and highlights the reduction of gender bias.

Contribution

It demonstrates that inclusive design approaches in AI explanations can create curb-cut effects, improving understanding and reducing gender bias, but may also have unintended negative impacts.

Findings

Increased user engagement with explanations due to inclusivity fixes

Improved mental model concepts scores from inclusivity fixes

Reduced gender gap by 45% through inclusive design

Abstract

Motivations: Explainable Artificial Intelligence (XAI) systems aim to improve users' understanding of AI, but XAI research shows many cases of different explanations serving some users well and being unhelpful to others. In non-AI systems, some software practitioners have used inclusive design approaches and sometimes their improvements turned out to be "curb-cut" improvements -- not only addressing the needs of underserved users, but also making the products better for everyone. So, if AI practitioners used inclusive design approaches, they too might create curb-cut improvements, i.e., better explanations for everyone. Objectives: To find out, we investigated the curb-cut effects of inclusivity-driven fixes on users' mental models of AI when using an XAI prototype. The prototype and fixes came from an AI team who had adopted an inclusive design approach (GenderMag) to improve their XAI prototype. Methods: We ran a between-subject study with 69 participants with no AI background. 34 participants used the original version of the XAI prototype and 35 used the version with the inclusivity fixes. We compared the two groups' mental model concepts scores, prediction accuracy, and inclusivity. Results: We found four main results. First, it revealed several curb-cut effects of the inclusivity fixes: overall increased engagement with explanations and better mental model concepts scores, which revealed fixes with curb-cut properties. However (second), the inclusivity fixes did not improve participants' prediction accuracy scores -- instead, it appears to have harmed them. This "curb-fence" effect (opposite of the curb-cut effect) revealed the AI explanations' double-edged impact. Third, the AI team's inclusivity fixes brought significant improvements for users whose problem-solving styles had previously been underserved. Further (fourth), the AI team's fixes reduced the gender gap by 45%.