A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making

TL;DR

This meta-analysis reviews existing research on explainable AI's impact on human decision-making, finding a generally positive effect, especially with text data, but no clear benefit from explanations alone.

Contribution

It provides the first statistical synthesis of XAI research, highlighting areas where explanations improve performance and identifying gaps for future investigation.

Findings

XAI has a statistically positive impact on user performance

Better task performance observed with text data in human-AI decision-making

No significant performance difference from explanations alone compared to AI predictions

Abstract

Research in artificial intelligence (AI)-assisted decision-making is experiencing tremendous growth with a constantly rising number of studies evaluating the effect of AI with and without techniques from the field of explainable AI (XAI) on human decision-making performance. However, as tasks and experimental setups vary due to different objectives, some studies report improved user decision-making performance through XAI, while others report only negligible effects. Therefore, in this article, we present an initial synthesis of existing research on XAI studies using a statistical meta-analysis to derive implications across existing research. We observe a statistically positive impact of XAI on users' performance. Additionally, the first results indicate that human-AI decision-making tends to yield better task performance on text data. However, we find no effect of explanations on users' performance compared to sole AI predictions. Our initial synthesis gives rise to future research investigating the underlying causes and contributes to further developing algorithms that effectively benefit human decision-makers by providing meaningful explanations.