Explainable Artificial Intelligence improves human decision-making: Results from a mushroom picking experiment at a public art festival

Abstract

Explainable Artificial Intelligence (XAI) enables an Artificial Intelligence (AI) to explain its decisions. This holds the promise of making AI more understandable to users, improving interaction, and establishing an adequate level of trust. We tested this assertion in the high-risk task of mushroom hunting, where users have to decide whether a mushroom is edible or poisonous with the aid of an AI-based app that suggests classifications based on mushroom images. In a between-subjects experiment N = 328 visitors of an Austrian media art exhibition played a mushroom hunting game on tablet computers while walking through a highly immersive artificial indoor forest. One group saw the AI's decisions only, while a second group additionally received attribution-based and example-based visual explanations of the AI's recommendation. The results show that participants with visual explanations outperformed participants without explanations in correct edibility assessments and pick-up decisions. This exhibition-based experiment thus replicated the decision-making results of a previous online study. However, unlike in the previous study, the visual explanations did not affect levels of trust or acceptance measures. In a direct comparison, we consequently discuss the findings in terms of generalizability. Besides the scientific contribution, we discuss the direct impact of conducting XAI experiments in highly immersive art- and game-based environments in exhibition contexts on visitors and local communities by triggering reflection and awareness for psychological issues of human-AI interaction.

Quantifying the impact of AI recommendations with explanations on prescription decision making: an interactive vignette study

“…2,3 However, most studies that practically evaluate whether and how explanations affect expert decision-making focus on general problems with lessons that do not necessarily translate to high complexity tasks in the clinical sphere. 4,5 In the few cases where medical XAI has been investigated with clinical experts, these have tended to focus on diagnostic scenarios for which a pre-existing gold standard exists with which to calculate accuracy. [6][7][8] This is not the case for many non-diagnostic medical problems such as the haemodynamic management of sepsis that affects millions of patients worldwide.…”

Impact of AI on Human Decision-Making: Analysis of Human, AI, and Environment of Interaction

“…XAI XAI, standing for eXplainable(X) Artificial(A) Intelligence(I), is "one that produces details or reasons to make its functioning clear or easy to understand" [4]. Leichtmann revealed that explanations of the AI's predictions would lead to a statistically significant better performance of decision-making through a mushroom-picking task [5]. Hudon also found that transparent and explainable AI systems could result in improved confidence between human and AI, which further have a positive impact on decision-making [6].…”