Strategies for improving the explainability of artificial agents are a key approach to support the understandability of artificial agents’ decision-making processes and their trustworthiness. However, since explanations are not inclined to standardization, finding solutions that fit the algorithmic-based decision-making processes of artificial agents poses a compelling challenge. This paper addresses the concept of trust in relation to complementary aspects that play a role in interpersonal and human–agent relationships, such as users’ confidence and their perception of artificial agents’ reliability. Particularly, this (...) paper focuses on non-expert users’ perspectives, since users with little technical knowledge are likely to benefit the most from “post-hoc”, everyday explanations. Drawing upon the explainable AI and social sciences literature, this paper investigates how artificial agent’s explainability and trust are interrelated at different stages of an interaction. Specifically, the possibility of implementing explainability as a trust building, trust maintenance and restoration strategy is investigated. To this extent, the paper identifies and discusses the intrinsic limits and fundamental features of explanations, such as structural qualities and communication strategies. Accordingly, this paper contributes to the debate by providing recommendations on how to maximize the effectiveness of explanations for supporting non-expert users’ understanding and trust. (shrink)

People often answer why-questions with what we call experiential explanations: narratives or stories with temporal structure and concrete details. In contrast, on most theories of the epistemic function of explanation, explanations should be abstractive: structured by general relationships and lacking extraneous details. We suggest that abstractive and experiential explanations differ not only in level of abstraction, but also in structure, and that each form of explanation contributes to the epistemic goals of individual learners and of science. In particular, experiential explanations (...) support mental simulation and survive transitions across background theories; as a result, they support learning and help us translate between competing frameworks. Experiential explanations play an irreducible role in human cognition – and perhaps in science. (shrink)

Our goal in this paper is to experimentally investigate whether folk conceptions of explanation are psychologistic. In particular, are people more likely to classify speech acts as explanations when they cause understanding in their recipient? The empirical evidence that we present suggests this is so. Using the side-effect effect as a marker of mental state ascriptions, we argue that lay judgments of explanatory status are mediated by judgments of a speaker’s and/or audience’s mental states. First, we show that attributions of (...) both understanding and explanation exhibit a side-effect effect. Next, we show that when the speaker’s and audience’s level of understanding is stipulated, the explanation side-effect effect goes away entirely. These results not only extend the side-effect effect to attributions of understanding, they also suggest that attributions of explanation exhibit a side-effect effect because they depend upon attributions of understanding, supporting the idea that folk conceptions of explanation are psychologistic. (shrink)

Cognitive Science, Volume 46, Issue 7, July 2022.

The capacity to search for information effectively by asking informative questions is crucial for self-directed learning and develops throughout the preschool years and beyond. We tested the hypothesis that explaining observations in a given domain prepares children to ask more informative questions in that domain, and that it does so by promoting the identification of features that apply to multiple objects, thus supporting more effective questions. Across two experiments, 4- to 7-year-old children (N = 168) were prompted to explain observed (...) evidence or to complete a control task prior to a 20-questions game. We found that prior prompts to explain led to a decrease in the number of questions needed to complete the game, but only for older children (ages 6-7). Moreover, we found that effects of explanation manifested as a shift away from questions that targeted single objects. These findings shed light on the development of question asking in childhood and on the role of explanation in learning. (shrink)

The literature on metaphysical explanation contains three widely accepted assumptions. First, that the notion of metaphysical explanation with which philosophers are interested is a notion with which the folk are familiar: it is at least continuous with the folk notion. Second, that metaphysical explanations are true propositions of a certain form that are true, (or false), simpliciter. Third, that it is at least the case that mostly, if x metaphysically explains y, then y does not metaphysically explain x. On the (...) basis of empirical investigations that we pursued, we argue that at least two of these assumptions are false . (shrink)

Le déficit d’explicabilité des techniques d’apprentissage machine (AM) pose des problèmes opérationnels, juridiques et éthiques. Un des principaux objectifs de notre projet est de fournir des explications éthiques des sorties générées par une application fondée sur de l’AM, considérée comme une boîte noire. La première étape de ce projet, présentée dans cet article, consiste à montrer que la validation de ces boîtes noires diffère épistémologiquement de celle mise en place dans le cadre d’une modélisation mathématique et causale d’un phénomène physique. (...) La différence majeure est qu’une méthode d’AM ne prétend pas représenter une causalité entre les paramètres d’entrées, qui peuvent être de plus de haute dimensionnalité, et ceux de sortie. Nous montrons dans cet article l’intérêt de mettre en œuvre les distinctions épistémologiques entre les différentes fonctions épistémiques d’un modèle, d’une part, et entre la fonction épistémique et l’usage d’un modèle, d’autre part. Enfin, la dernière partie de cet article présente nos travaux en cours sur l’évaluation d’une explication, qui peut être plus persuasive qu’informative, ce qui peut ainsi causer des problèmes d’ordre éthique. (shrink)

Advancements and deployments of AI-based systems, especially Deep Learning-driven generative language models, have accomplished impressive results over the past few years. Nevertheless, these remarkable achievements are intertwined with a related fear that such technologies might lead to a general relinquishing of our lives’s control to AIs. This concern, which also motivates the increasing interest in the eXplainable Artificial Intelligence (XAI) research field, is mostly caused by the opacity of the output of deep learning systems and the way that it is (...) generated, which is largely obscure to laypeople. A dialectical interaction with such systems may enhance the users’ understanding and build a more robust trust towards AI. Commonly employed as specific formalisms for modelling intra-agent communications, dialogue games prove to be useful tools to rely upon when dealing with user’s explanation needs. The literature already offers some dialectical protocols that expressly handle explanations and their delivery. This paper fully formalises the novel Explanation–Question–Response (EQR) dialogue and its properties, whose main purpose is to provide satisfactory information (i.e., justified according to argumentative semantics) whilst ensuring a simplified protocol, in comparison with other existing approaches, for humans and artificial agents. (shrink)

Explanations are conceived to ensure the trustworthiness of AI systems. Yet, relying solemnly on algorithmic solutions, as provided by explainable artificial intelligence (XAI), might fall short to account for sociotechnical risks jeopardizing their factuality and informativeness. To mitigate these risks, we delve into the complex landscape of ethical risks surrounding XAI systems and their generated explanations. By employing a literature review combined with rigorous thematic analysis, we uncover a diverse array of technical risks tied to the robustness, fairness, and evaluation (...) of XAI systems. Furthermore, we address a broader range of contextual risks jeopardizing their security, accountability, reception alongside other cognitive, social, and ethical concerns of explanations. We advance a multi-layered risk assessment framework, where each layer advances strategies for practical intervention, management, and documentation of XAI systems within organizations. Recognizing the theoretical nature of the framework advanced, we discuss it in a conceptual case study. For the XAI community, our multifaceted investigation represents a path to practically address XAI risks while enriching our understanding of the ethical ramifications of incorporating XAI in decision-making processes. (shrink)