Explainable Artificial Intelligence (XAI) enables 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 claim in the high-risk task of AI-assisted mushroom hunting, where people had to decide whether a mushroom was edible or poisonous. In a between-subjects experiment, 328 visitors of an Austrian media art festival played a tablet-based mushroom hunting game while walking through a highly immersive artificial indoor forest. As part of the game, an artificially intelligent app analyzed photos of the mushrooms they found and recommended classifications. 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 significantly 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 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.

Trust calibration is essential in AI-assisted decision-making. If human users understand the rationale on which an AI model has made a prediction, they can decide whether they consider this prediction reasonable. Especially in high-risk tasks such as mushroom hunting (where a wrong decision may be fatal), it is important that users make correct choices to trust or overrule the AI. Various explainable AI (XAI) methods are currently being discussed as potentially useful for facilitating understanding and subsequently calibrating user trust. So far, however, it remains unclear which approaches are most effective. In this article, the effects of XAI methods on human AI-assisted decision-making in the high-risk task of mushroom picking were tested. For that endeavor, the effects of (i) Grad-CAM attributions, (ii) nearest-neighbor examples, and (iii) network-dissection concepts were compared in a between-subjects experiment with \(N=501\) participants representing end-users of the system. In general, nearest-neighbor examples improved decision correctness the most. However, varying effects for different task items became apparent. All explanations seemed to be particularly effective when they revealed reasons to (i) doubt a specific AI classification when the AI was wrong and (ii) trust a specific AI classification when the AI was correct. Our results suggest that well-established methods, such as Grad-CAM attribution maps, might not be as beneficial to end users as expected and that XAI techniques for use in real-world scenarios must be chosen carefully.

ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space while minimizing an objective function. ParaDime builds on the idea that the objective functions of several modern DR techniques result from transformed inter-item relationships. It provides a common interface for specifying these relations and transformations and for defining how they are used within the losses that govern the training process. Through this interface, ParaDime unifies parametric versions of DR techniques such as metric MDS, t-SNE, and UMAP. It allows users to fully customize all aspects of the DR process. We show how this ease of customization makes ParaDime suitable for experimenting with interesting techniques such as hybrid classification/embedding models and supervised DR. This way, ParaDime opens up new possibilities for visualizing high-dimensional data.

In this work, we propose an interactive visual approach for the exploration and formation of structural relationships in embeddings of high-dimensional data. These structural relationships, such as item sequences, associations of items with groups, and hierarchies between groups of items, are defining properties of many real-world datasets. Nevertheless, most existing methods for the visual exploration of embeddings treat these structures as second-class citizens or do not take them into account at all. In our proposed analysis workflow, users explore enriched scatterplots of the embedding, in which relationships between items and/or groups are visually highlighted. The original high-dimensional data for single items, groups of items, or differences between connected items and groups are accessible through additional summary visualizations. We carefully tailored these summary and difference visualizations to the various data types and semantic contexts. During their exploratory analysis, users can externalize their insights by setting up additional groups and relationships between items and/or groups. We demonstrate the utility and potential impact of our approach by means of two use cases and multiple examples from various domains.