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

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 decisionmaking 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. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI; • Computing methodologies → Artificial intelligence.

An Empirical Evaluation of Estimated Outcomes as Explanations in Human-AI Decision-Making

“…Despite these claims, recent research shows that XAI does not necessarily improve human-AI decision-making over cases where no explanations are provided [2,15,37]. Even worse, [34] find that providing people with an interpretable model can result in less accurate predictions.…”

“…Prior research already discovered that XAI can have effects on reliance. While many studies report XAI leading to over-reliance [38], the effect demands fur-ther investigation [37]. The results of multiple studies remain inconclusive, some pointing towards over-reliance [10,39], some to under-reliance [31,36].…”