Research about explanation processes is gaining relevance because of the increased popularity of artificial systems required to explain their function or outcome. Following an interactive approach, not only explainers, but also explainees contribute to successful interactions. However, little is known about how explainees actively guide explanation processes and how their involvement relates to learning. We explored the occurrence and type of explainees’ questions in 20 adult — adult explanation dialogues about unknown present and absent objects. Crucially, we related the question (...) types to the explainees’ subsequent recall of the unknown object labels. We found that explainees asked different types of questions, especially about the object’s label and facts. Questions about the object’s function were asked more when objects were present. In addition, requests for labelling were linked to better recall. The results contribute to designing explainable AI that aims to provide relevant and adaptive explanations and to further experimental approaches to study explanations. (shrink)

In this paper we argue that transparency of machine learning algorithms, just as explanation, can be defined at different levels of abstraction. We criticize recent attempts to identify the explanation of black box algorithms with making their decisions (post-hoc) interpretable, focusing our discussion on counterfactual explanations. These approaches to explanation simplify the real nature of the black boxes and risk misleading the public about the normative features of a model. We propose a new form of algorithmic transparency, that consists in (...) explaining algorithms as an intentional product, that serves a particular goal, or multiple goals (Daniel Dennet’s design stance) in a given domain of applicability, and that provides a measure of the extent to which such a goal is achieved, and evidence about the way that measure has been reached. We call such idea of algorithmic transparency “design publicity.” We argue that design publicity can be more easily linked with the justification of the use and of the design of the algorithm, and of each individual decision following from it. In comparison to post-hoc explanations of individual algorithmic decisions, design publicity meets a different demand (the demand for impersonal justification) of the explainee. Finally, we argue that when models that pursue justifiable goals (which may include fairness as avoidance of bias towards specific groups) to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are (unavoidably) based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions. (shrink)

Since the emergence of the field of eXplainable Artificial Intelligence (XAI), a growing number of researchers have argued that XAI should consider insights from the social sciences in order to adapt explanations to the expectations and needs of human users. This has led to the emergence of a field called Social XAI, which is concerned with understanding how explanations are actively shaped in the interaction between a human user and an AI system. Recognizing this turn in XAI toward making XAI (...) systems more “social” by providing explanations that focus on human information needs and incorporating insights from human–human explanatory interactions, in this paper we provide a formal foundation for Social XAI. We do so by proposing novel ontological accounts of the key terms used in Social XAI based on Basic Formal Ontology (BFO). Specifically, we provide novel ontological accounts for explanandum, explanans, understanding, explanation, explainer, explainee, and context. In doing so, we discuss multifaceted entities in Social XAI (having both continuant and occurrent facets; e.g., explanation) and the relationship between understanding and explanation. Additionally, we propose solutions to seemingly paradoxical views on some terms (e.g., social constructivist vs. individual constructivist perspective on explanandum). (shrink)

In this note, we discuss the possibility of humansplaining, where humansplaining is, in analogy to mansplaining, a human's act of unnecessarily and unjustly explaining something to an AI agent who is an expert on that topic. We argue that, assuming a suitably developed AI which is capable of being explained to in the first place, humansplaining would be bad for similar reasons as mansplaining and that the risk one runs of engaging in it would vary depending on the explained topic (...) and in particular on whether the natures of the explainer, the explainee, or both allow them to have expertise in that area. (shrink)

A widespread need to explain the behavior and outcomes of AI-based systems has emerged, due to their ubiquitous presence. Thus, providing renewed momentum to the relatively new research area of eXplainable AI (XAI). Nowadays, the importance of XAI lies in the fact that the increasing control transference to this kind of system for decision making -or, at least, its use for assisting executive stakeholders- already affects many sensitive realms (as in Politics, Social Sciences, or Law). The decision-making power handover to (...) opaque AI systems makes mandatory explaining those, primarily in application scenarios where the stakeholders are unaware of both the high technology applied and the basic principles governing the technological solutions. The issue should not be reduced to a merely technical problem; the explainer would be compelled to transmit richer knowledge about the system (including its role within the informational ecosystem where he/she works). To achieve such an aim, the explainer could exploit, if necessary, practices from other scientific and humanistic areas. The first aim of the paper is to emphasize and justify the need for a multidisciplinary approach that is beneficiated from part of the scientific and philosophical corpus on Explaining, underscoring the particular nuances of the issue within the field of Data Science. The second objective is to develop some arguments justifying the authors’ bet by a more relevant role of ideas inspired by, on the one hand, formal techniques from Knowledge Representation and Reasoning, and on the other hand, the modeling of human reasoning when facing the explanation. This way, explaining modeling practices would seek a sound balance between the pure technical justification and the explainer-explainee agreement. (shrink)

Everyday explanations are interactive processes with the aim to provide a less knowledgeable person with reasonable information about other people, objects, or events. Because explanations are interactive communicative processes, the topical structure of an explanation may vary dynamically depending on the immediate feedback of the explainee. In this paper, we analyse topical transitions in medical explanations organised by different physicians (explainers) related to different forms of multimodal behaviour of caregivers (explainees) attending an explanation about the procedures of an upcoming (...) surgery of a child. The analyses reveal that explainees’ multimodal behaviour with gaze shifts (and particularly gaze aversion) can predict a transition from an elaborated topic to a new one, whereas explainees’ forms of multimodal behaviour with static gaze cannot be related to changes of the topical structure. (shrink)

In this paper I explore a method for refusing uptake when explanations are morally and epistemically troubling. Gaile Pohlhaus Jr has shown that imploring marginalised people to “understand” marginalising practices amounts to a request that they legitimise their own marginalisation. In this paper, I expand upon this analysis with the aim of describing a method for withholding understanding. First, I analyse understanding through its association with explanation. Drawing on pragmatic theories, I describe explanations as speech acts whose success depends on (...) the explainee granting the explainer uptake by revising their background assumptions. Those background assumptions sometimes reference troubling generalisations, and in those cases, the explanation must be blocked. Accordingly, I formalise a form of explanatory resistance in which the explainee feigns misunderstanding to corner the explainer into exposing the problematic assumptions upon which their explanation depends. Second, I situate wrongful requests for understanding within the epistemic injustice schema as “explanatory injustices,” emphasising the fact that marginalised groups are also specifically marginalised within the explanation economy. I conclude that we should be more cognisant of the way in which explanations track power, and be prepared to undertake resistance in order to expose moral and epistemic shortcomings in how we explain. (shrink)