Modern explainable AI methods remain far from providing human-like answers to ‘why’ questions, let alone those that satisfactorily agree with human-level understanding. Instead, the results that such methods provide boil down to sets of causal attributions. Currently, the choice of accepted attributions rests largely, if not solely, on the explainee’s understanding of the quality of explanations. The paper argues that such decisions may be transferred from a human to an XAI agent, provided that its machine-learning algorithms perform genuinely abductive (...) inferences. The paper outlines the key predicament in the current inductive paradigm of ML and the associated XAI techniques, and sketches the desiderata for a truly participatory, second-generation XAI, which is endowed with abduction. (shrink)

The counterfactual approach to explainable AI (XAI) seeks to provide understanding of AI systems through the provision of counterfactual explanations. In a recent systematic review, Chou et al. (Inform Fus 81:59–83, 2022) argue that the counterfactual approach does not clearly provide causal understanding. They diagnose the problem in terms of the underlying framework within which the counterfactual approach has been developed. To date, the counterfactual approach has not been developed in concert with the approach for specifying causes developed by (...) Pearl (Causality: Models, reasoning, and inference. Cambridge University Press, 2000) and Woodward (Making things happen: A theory of causal explanation. Oxford University Press, 2003). In this paper, I build on Chou et al.’s work by applying the Pearl-Woodward approach. I argue that the standard counterfactual approach to XAI is capable of delivering causal understanding, but that there are limitations on its capacity to do so. I suggest a way to overcome these limitations. (shrink)

Many artificial intelligence (AI) systems currently used for decision-making are opaque, i.e., the internal factors that determine their decisions are not fully known to people due to the systems’ computational complexity. In response to this problem, several researchers have argued that human decision-making is equally opaque and since simplifying, reason-giving explanations (rather than exhaustive causal accounts) of a decision are typically viewed as sufficient in the human case, the same should hold for algorithmic decision-making. Here, I contend that this argument (...) overlooks that human decision-making is sometimes significantly more transparent and trustworthy than algorithmic decision-making. This is because when people explain their decisions by giving reasons for them, this frequently prompts those giving the reasons to govern or regulate themselves so as to think and act in ways that confirm their reason reports. AI explanation systems lack this self-regulative feature. Overlooking it when comparing algorithmic and human decision-making can result in underestimations of the transparency of human decision-making and in the development of explainable AI that may mislead people by activating generally warranted beliefs about the regulative dimension of reason-giving. (shrink)

The apparent downsides of opaque algorithms has led to a demand for explainable AI (XAI) methods by which a user might come to understand why an algorithm produced the particular output it did, given its inputs. Patients, for example, might find that the lack of explanation of the process underlying the algorithmic recommendations for diagnosis and treatment hinders their ability to provide informed consent. This paper examines the impact of two factors on user perceptions of explanations for AI systems (...) in medical contexts. The factors considered were the stakes of the decision—high versus low—and the decision source—human versus AI. 484 participants were presented with vignettes in which medical diagnosis and treatment plan recommendations were made by humans or by AI. Separate vignettes were used for high stakes scenarios involving life-threatening diseases, and low stakes scenarios involving mild diseases. In each vignette, an explanation for the decision was given. Four explanation types were tested across separate vignettes: no explanation, counterfactual, causal and a novel ‘narrative-based’ explanation, not previously considered. This yielded a total of 16 conditions, of which each participant saw only one. Individuals were asked to evaluate the explanations they received based on helpfulness, understanding, consent, reliability, trust, interests and likelihood of undergoing treatment. We observed a main effect for stakes on all factors and a main effect for decision source on all factors except for helpfulness and likelihood to undergo treatment. While we observed effects for explanation on helpfulness, understanding, consent, reliability, trust and interests, we by and large did not see any differences between the effects of explanation types. This suggests that the effectiveness of explanations may not depend on type of explanation but instead, on the stakes and decision source. (shrink)

Many AI systems that make important decisions are black boxes: how they function is opaque even to their developers. This is due to their high complexity and to the fact that they are trained rather than programmed. Efforts to alleviate the opacity of black box systems are typically discussed in terms of transparency, interpretability, and explainability. However, there is little agreement about what these key concepts mean, which makes it difficult to adjudicate the success or promise of opacity alleviation methods. (...) I argue for a unified account of these key concepts that treats the concept of understanding as fundamental. This allows resources from the philosophy of science and the epistemology of understanding to help guide opacity alleviation efforts. A first significant benefit of this understanding account is that it defuses one of the primary, in-principle objections to post hoc explainable AI (XAI) methods. This “rationalization objection” argues that XAI methods provide mere rationalizations rather than genuine explanations. This is because XAI methods involve using a separate “explanation” system to approximate the original black box system. These explanation systems function in a completely different way than the original system, yet XAI methods make inferences about the original system based on the behavior of the explanation system. I argue that, if we conceive of XAI methods as idealized scientific models, this rationalization worry is dissolved. Idealized scientific models misrepresent their target phenomena, yet are capable of providing significant and genuine understanding of their targets. (shrink)

This paper shows that the law, in subtle ways, may set hitherto unrecognized incentives for the adoption of explainable machine learning applications. In doing so, we make two novel contributions. First, on the legal side, we show that to avoid liability, professional actors, such as doctors and managers, may soon be legally compelled to use explainable ML models. We argue that the importance of explainability reaches far beyond data protection law, and crucially influences questions of contractual and tort (...) liability for the use of ML models. To this effect, we conduct two legal case studies, in medical and corporate merger applications of ML. As a second contribution, we discuss the trade-off between accuracy and explainability and demonstrate the effect in a technical case study in the context of spam classification. (shrink)

Artificial intelligence (AI) has become nearly ubiquitous in modern society, from components of mobile applications to medical support systems, and everything in between. In societally impactful systems imbued with AI, there has been increasing concern related to opaque AI, that is, artificial intelligence where it is unclear how or why certain decisions are reached. This has led to a recent boom in research on “explainable AI” (XAI), or approaches to making AI more explainable and understandable to human users. (...) In the military domain, numerous bodies have argued that autonomous and AI-enabled weapon systems ought not incorporate unexplainable AI, with the International Committee of the Red Cross and the United States Department of Defense both explicitly including explainability as a relevant factor in the development and use of such systems. In this article, I present a cautiously critical assessment of this view, arguing that explainability will be irrelevant for many current and near-future autonomous systems in the military (which do not incorporate any AI), that it will be trivially incorporated into most military systems which do possess AI (as these generally possess simpler AI systems), and that for those systems with genuinely opaque AI, explainability will prove to be of more limited value than one might imagine. In particular, I argue that explainability, while indeed a virtue in design, is a virtue aimed primarily at designers and troubleshooters of AI-enabled systems, but is far less relevant for users and handlers actually deploying these systems. I further argue that human–machine teaming is a far more important element of responsibly using AI for military purposes, adding that explainability may undermine efforts to improve human–machine teamings by creating aprima faciesense that the AI, due to its explainability, may be utilized with little (or less) potential for mistakes. I conclude by clarifying that the arguments are not against XAI in the military, but are instead intended as a caution against over-inflating the value of XAI in this domain, or ignoring the limitations and potential pitfalls of this approach. (shrink)

When artificial intelligence (AI) is used to make high-stakes decisions, some worry that this will create a morally troubling responsibility gap—that is, a situation in which nobody is morally responsible for the actions and outcomes that result. Since the responsibility gap might be thought to result from individuals lacking knowledge of the future behavior of AI systems, it can be and has been suggested that deploying explainable artificial intelligence (XAI) techniques will help us to avoid it. These techniques provide (...) humans with certain forms of understanding of the systems in question. In this paper, I consider whether existing XAI techniques can indeed close the responsibility gap. I identify a number of significant limits to their ability to do so. Ensuring that responsibility for AI-assisted outcomes is maintained may require using different techniques in different circumstances, and potentially also developing new techniques that can avoid each of the issues identified. (shrink)

There is a current debate about if, and in what sense, machine learning systems used in the medical context need to be explainable. Those arguing in favor contend these systems require post hoc explanations for each individual decision to increase trust and ensure accurate diagnoses. Those arguing against suggest the high accuracy and reliability of the systems is sufficient for providing epistemic justified beliefs without the need for explaining each individual decision. But, as we show, both solutions have limitations—and (...) it is unclear either address the epistemic worries of the medical professionals using these systems. We argue these systems do require an explanation, but an institutional explanation. These types of explanations provide the reasons why the medical professional should rely on the system in practice—that is, they focus on trying to address the epistemic concerns of those using the system in specific contexts and specific occasions. But ensuring that these institutional explanations are fit for purpose means ensuring the institutions designing and deploying these systems are transparent about the assumptions baked into the system. This requires coordination with experts and end-users concerning how it will function in the field, the metrics used to evaluate its accuracy, and the procedures for auditing the system to prevent biases and failures from going unaddressed. We contend this broader explanation is necessary for either post hoc explanations or accuracy scores to be epistemically meaningful to the medical professional, making it possible for them to rely on these systems as effective and useful tools in their practices. (shrink)

Recent work in explainable artificial intelligence (XAI) attempts to render opaque AI systems understandable through a divide-and-conquer strategy. However, this fails to illuminate how trained AI systems work as a whole. Precisely this kind of functional understanding is needed, though, to satisfy important societal desiderata such as safety. To remedy this situation, we argue, AI researchers should seek mechanistic interpretability, viz. apply coordinated discovery strategies familiar from the life sciences to uncover the functional organisation of complex AI systems. Additionally, (...) theorists should accommodate for the unique costs and benefits of such strategies in their portrayals of XAI research. (shrink)

For synergistic interactions between humans and artificial intelligence (AI) systems, AI outputs often need to be explainable to people. Explainable AI (XAI) systems are commonly tested in human user studies. However, whether XAI researchers consider potential cultural differences in human explanatory needs remains unexplored. We highlight psychological research that found significant differences in human explanations between many people from Western, commonly individualist countries and people from non-Western, often collectivist countries. We argue that XAI research currently overlooks these variations (...) and that many popular XAI designs implicitly and problematically assume that Western explanatory needs are shared cross-culturally. Additionally, we systematically reviewed over 200 XAI user studies and found that most studies did not consider relevant cultural variations, sampled only Western populations, but drew conclusions about human-XAI interactions more generally. We also analyzed over 30 literature reviews of XAI studies. Most reviews did not mention cultural differences in explanatory needs or flag overly broad cross-cultural extrapolations of XAI user study results. Combined, our analyses provide evidence of a cultural bias toward Western populations in XAI research, highlighting an important knowledge gap regarding how culturally diverse users may respond to widely used XAI systems that future work can and should address. (shrink)

This paper analyses whether current explainable AI (XAI) techniques can help to address taxpayer concerns about the use of AI in taxation. As tax authorities around the world increase their use of AI-based techniques, taxpayers are increasingly at a loss about whether and how the ensuing decisions follow the procedures required by law and respect their substantive rights. The use of XAI has been proposed as a response to this issue, but it is still an open question whether current (...) XAI techniques are enough to meet existing legal requirements. The paper approaches this question in the context of a case study: a prototype tax fraud detector trained on an anonymized dataset of real-world cases handled by the Buenos Aires (Argentina) tax authority. The decisions produced by this detector are explained through the use of various classification methods, and the outputs of these explanation models are evaluated on their explanatory power and on their compliance with the legal obligation that tax authorities provide the rationale behind their decision-making. We conclude the paper by suggesting technical and legal approaches for designing explanation mechanisms that meet the needs of legal explanation in the tax domain. (shrink)

Many ethical frameworks require artificial intelligence (AI) systems to be explainable. Explainable AI (XAI) models are frequently tested for their adequacy in user studies. Since different people may have different explanatory needs, it is important that participant samples in user studies are large enough to represent the target population to enable generalizations. However, it is unclear to what extent XAI researchers reflect on and justify their sample sizes or avoid broad generalizations across people. We analyzed XAI user studies (...) (N = 220) published between 2012 and 2022. Most studies did not offer rationales for their sample sizes. Moreover, most papers generalized their conclusions beyond their target population, and there was no evidence that broader conclusions in quantitative studies were correlated with larger samples. These methodological problems can impede evaluations of whether XAI systems implement the explainability called for in ethical frameworks. We outline principles for more inclusive XAI user studies. (shrink)

Artificial intelligence (AI) systems are increasingly adopted to make decisions in domains such as business, education, health care, and criminal justice. However, such algorithmic decision systems can have prevalent biases against marginalized social groups and undermine social justice. Explainable artificial intelligence (XAI) is a recent development aiming to make an AI system’s decision processes less opaque and to expose its problematic biases. This paper argues against technical XAI, according to which the detection and interpretation of algorithmic bias can be (...) handled more or less independently by technical experts who specialize in XAI methods. Drawing on resources from feminist epistemology, we show why technical XAI is mistaken. Specifically, we demonstrate that the proper detection of algorithmic bias requires relevant interpretive resources, which can only be made available, in practice, by actively involving a diverse group of stakeholders. Finally, we suggest how feminist theories can help shape integrated XAI: an inclusive social-epistemic process that facilitates the amelioration of algorithmic bias. (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)

In this paper, we contribute to research on enterprise artificial intelligence (AI), specifically to organizations improving the customer experiences and their internal processes through using the type of AI called machine learning (ML). Many organizations are struggling to get enough value from their AI efforts, and part of this is related to the area of explainability. The need for explainability is especially high in what is called black-box ML models, where decisions are made without anyone understanding how an AI reached (...) a particular decision. This opaqueness creates a user need for explanations. Therefore, researchers and designers create different versions of so-called eXplainable AI (XAI). However, the demands for XAI can reduce the accuracy of the predictions the AI makes, which can reduce the perceived usefulness of the AI solution, which, in turn, reduces the interest in designing the organizational task structure to benefit from the AI solution. Therefore, it is important to ensure that the need for XAI is as low as possible. In this paper, we demonstrate how to achieve this by optimizing the task structure according to sociotechnical systems design principles. Our theoretical contribution is to the underexplored field of the intersection of AI design and organizational design. We find that explainability goals can be divided into two groups, pattern goals and experience goals, and that this division is helpful when defining the design process and the task structure that the AI solution will be used in. Our practical contribution is for AI designers who include organizational designers in their teams, and for organizational designers who answer that challenge. (shrink)

Objective: This study aimed to explore the relationship among cognitive fusion, experiential avoidance, and obsessive–compulsive symptoms in patients with obsessive–compulsive disorder.Methods: A total of 118 outpatient and inpatient patients with OCD and 109 healthy participants, gender- and age-matched, were selected using cognitive fusion questionnaire, acceptance and action questionnaire−2nd edition, Yale–Brown scale for obsessive–compulsive symptoms, Hamilton anxiety scale, and Hamilton depression scale for questionnaire testing and data analysis.Results: The levels of cognitive fusion and experiential avoidance in the OCD group were significantly (...) higher than those in the healthy control group. Regression analysis results showed that, in predicting the total score of obsessive–compulsive symptoms, AAQ-II and CFQ entered the equation, which explained 17.1% variance. In predicting anxiety, only AAQ-II entered the equation, which explained 13% variance. In the prediction of depression, AAQ-II entered the equation, which explained 17.7% variance.Conclusion: Cognitive fusion and experiential avoidance may be important factors for the maintenance of OCD, and experiential avoidance can positively predict the anxiety and depression of OCD patients. (shrink)

In recent years, research in robotics and artificial intelligence (AI) has made rapid progress. It is expected that robots and AI will play a part in the field of nursing and their role might broaden in the future. However, there are areas of nursing practice that cannot or should not be entrusted to robots and AI, because nursing is a highly humane practice, and therefore, there would, perhaps, be some practices that should not be replicated by robots or AI. Therefore, (...) this paper focuses on several ethical concepts (advocacy, accountability, cooperation, and caring) that are considered important in nursing practice, and examines whether it is possible to implement these ethical concepts in robots and AI by analyzing the concepts and the current state of robotics and AI technology. Advocacy: Among the components of advocacy, safeguarding and apprising can be more easily implemented, while elements that require emotional communication with patients, such as valuing and mediating, are difficult to implement. Accountability: Robotic nurses with explainable AI have a certain level of accountability. However, the concept of explanation has problems of infinite regression and attribution of responsibility. Cooperation: If robot nurses are recognized as members of a community, they require the same cooperation as human nurses. Caring: More difficulties are expected in care-receiving than in caregiving. However, the concept of caring itself is ambiguous and should be explored further. Accordingly, our analysis suggests that, although some difficulties can be expected in each of these concepts, it cannot be said that it is impossible to implement them in robots and AI. However, even if it were possible to implement these functions in the future, further study is needed to determine whether such robots or AI should be used for nursing care. In such discussions, it will be necessary to involve not only ethicists and nurses but also an array of society members. (shrink)

Artificial intelligence tools used in employment decision-making cut across the multiple stages of job advertisements, shortlisting, interviews and hiring, and actual and potential bias can arise in each of these stages. One major challenge is to mitigate AI bias and promote fairness in opaque AI systems. This paper argues that the equal opportunity merit principle is an ethical approach for fair AI employment decision-making. Further, explainable AI can mitigate the opacity problem by placing greater emphasis on enhancing the understanding (...) of reasonable users and affected persons as to the AI output. Both the equal opportunity merit principle and explainable AI should be integrated in the design and implementation of AI employment decision-making systems so as to ensure, as far as possible, that the AI output is arrived at through a fair process. (shrink)

To create fair and accountable AI and robotics, we need precise regulation and better methods to certify, explain, and audit inscrutable systems.

With its potential to contribute to the ethical governance of AI, eXplainable AI (XAI) research frequently asserts its relevance to ethical considerations. Yet, the substantiation of these claims with rigorous ethical analysis and reflection remains largely unexamined. This contribution endeavors to scrutinize the relationship between XAI and ethical considerations. By systematically reviewing research papers mentioning ethical terms in XAI frameworks and tools, we investigate the extent and depth of ethical discussions in scholarly research. We observe a limited and often (...) superficial engagement with ethical theories, with a tendency to acknowledge the importance of ethics, yet treating it as a monolithic and not contextualized concept. Our findings suggest a pressing need for a more nuanced and comprehensive integration of ethics in XAI research and practice. To support this, we propose to critically reconsider transparency and explainability in regards to ethical considerations during XAI systems design while accounting for ethical complexity in practice. As future research directions, we point to the promotion of interdisciplinary collaborations and education, also for underrepresented ethical perspectives. Such ethical grounding can guide the design of ethically robust XAI systems, aligning technical advancements with ethical considerations. (shrink)

Providing meaningful and actionable explanations for end-users is a situated problem requiring the intersection of multiple disciplines to address social, operational, and technical challenges. However, the explainable artificial intelligence community has not commonly adopted or created tangible design tools that allow interdisciplinary work to develop reliable AI-powered solutions. This paper proposes a formative architecture that defines the explanation space from a user-inspired perspective. The architecture comprises five intertwined components to outline explanation requirements for a task: (1) the end-users’ mental (...) models, (2) the end-users’ cognitive process, (3) the user interface, (4) the Human-Explainer Agent, and (5) the agent process. We first define each component of the architecture. Then, we present the Abstracted Explanation Space, a modeling tool that aggregates the architecture’s components to support designers in systematically aligning explanations with end-users’ work practices, needs, and goals. It guides the specifications of what needs to be explained (content: end-users’ mental model), why this explanation is necessary (context: end-users’ cognitive process), to delimit how to explain it (format: Human-Explainer Agent and user interface), and when the explanations should be given. We then exemplify the tool’s use in an ongoing case study in the aircraft maintenance domain. Finally, we discuss possible contributions of the tool, known limitations or areas for improvement, and future work to be done. (shrink)

In the past few years, machine learning (ML) tools have been implemented with success in the medical context. However, several practitioners have raised concerns about the lack of transparency—at the algorithmic level—of many of these tools; and solutions from the field of explainable AI (XAI) have been seen as a way to open the ‘black box’ and make the tools more trustworthy. Recently, Alex London has argued that in the medical context we do not need machine learning tools to (...) be interpretable at the algorithmic level to make them trustworthy, as long as they meet some strict empirical desiderata. In this paper, we analyse and develop London’s position. In particular, we make two claims. First, we claim that London’s solution to the problem of trust can potentially address another problem, which is how to evaluate the reliability of ML tools in medicine for regulatory purposes. Second, we claim that to deal with this problem, we need to develop London’s views by shifting the focus from the opacity of algorithmic details to the opacity of the way in which ML tools are trained and built. We claim that to regulate AI tools and evaluate their reliability, agencies need an explanation of how ML tools have been built, which requires documenting and justifying the technical choices that practitioners have made in designing such tools. This is because different algorithmic designs may lead to different outcomes, and to the realization of different purposes. However, given that technical choices underlying algorithmic design are shaped by value-laden considerations, opening the black box of the design process means also making transparent and motivating (technical and ethical) values and preferences behind such choices. Using tools from philosophy of technology and philosophy of science, we elaborate a framework showing how an explanation of the training processes of ML tools in medicine should look like. (shrink)

There has been a surge of interest in explainable artificial intelligence (XAI). It is commonly claimed that explainability is necessary for trust in AI, and that this is why we need it. In this paper, I argue that for some notions of trust it is plausible that explainability is indeed a necessary condition. But that these kinds of trust are not appropriate for AI. For notions of trust that are appropriate for AI, explainability is not a necessary condition. I (...) thus conclude that explainability is not necessary for trust in AI that matters. (shrink)

Based on the expanded theory of planned behavior, this study first explores the configuration relationship between founder management and innovation by using the fuzzy-set qualitative comparative analysis. Based on the theory of planned behavior, this study divides the behavior intention of founders into three categories: Attitude, subjective norm, and perceived behavior control. Using fsQCA, we found that there are two ways to achieve high innovation input of enterprises. In combination with the two ways, the factors such as male and highly (...) educated founder, and large firm size can effectively increase the innovation input of firms, which is consistent with the three aspects of the behavioral intention of the theory of planned behavior, and it proves that the theory of planned behavior can effectively explain the configuration relation between the founder and firm innovation. In addition, this study finds that the innovation output is different from the innovation input, is dependent on the innovation ability of the firm itself, and is less influenced by the external environment. (shrink)

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it’s important to remember Box’s maxim that "All models are wrong but some are useful." We focus on (...) the distinction between these models and explanations in philosophy and sociology. These models can be understood as a "do it yourself kit" for explanations, allowing a practitioner to directly answer "what if questions" or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly. (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)

One of the primary, if not most critical, difficulties in the design and implementation of autonomous systems is the black-boxed nature of the decision-making structures and logical pathways. How human values are embodied and actualised in situ may ultimately prove to be harmful if not outright recalcitrant. For this reason, the values of stakeholders become of particular significance given the risks posed by opaque structures of intelligent agents (IAs). This paper explores how decision matrix algorithms, via the belief-desire-intention model for (...) autonomous vehicles, can be designed to minimize the risks of opaque architectures. Primarily through an explicit orientation towards designing for the values of explainability and verifiability. In doing so, this research adopts the Value Sensitive Design (VSD) approach as a principled framework for the incorporation of such values within design. VSD is recognized as a potential starting point that offers a systematic way for engineering teams to formally incorporate existing technical solutions within ethical design, while simultaneously remaining pliable to emerging issues and needs. It is concluded that the VSD methodology offers at least a strong enough foundation from which designers can begin to anticipate design needs and formulate salient design flows that can be adapted to the changing ethical landscapes required for utilisation in autonomous vehicles. (shrink)

There has been a push in recent years to provide better explanations for how AIs make their decisions. Most of this push has come from the ethical concerns that go hand in hand with AIs making decisions that affect humans. Outside of the strictly ethical concerns that have prompted the study of explainable AIs (XAIs), there has been research interest in the mere possibility of creating XAIs in various domains. In general, the more accurate we make our models the (...) harder they are to explain. Go playing AIs like AlphaGo and KataGo provide fantastic examples of this phenomenon. In this paper, I discuss a non-exhaustive list of the leading theories of explanation and what each of these theories would say about the explainability of AI-played moves of Go. Finally, I consider the possibility of ever explaining AI-played Go moves in a way that meets the four principles of XAI. I conclude, somewhat pessimistically, that Go is not as imminently explainable as other domains. As such, the probability of having an XAI for Go that meets the four principles is low. (shrink)

Wrocław University of Science and Technology, Poland This article is a review of the book _Making AI Intelligible. Philosophical Foundations_, written by Herman Cappelen and Josh Dever, and published in 2021 by Oxford University Press. The authors of the reviewed book address the difficult issue of interpreting the results provided by AI systems and the links between human-specific content handling and the internal mechanisms of these systems. Considering the potential usefulness of various frameworks developed in philosophy to solve the problem, (...) they conduct a thorough analysis of a wide spectrum of them, from the use of Saul Kripke’s work to a critical analysis of the explainable AI current. (shrink)

Machine learning-based AI algorithms lack transparency. In this article, I offer an interpretation of AI’s explainability problem and highlight its ethical saliency. I try to make the case for the legal enforcement of a strong explainability requirement: human organizations which decide to automate decision-making should be legally obliged to demonstrate the capacity to explain and justify the algorithmic decisions that have an impact on the wellbeing, rights, and opportunities of those affected by the decisions. This legal duty can be derived (...) from the demands of Rawlsian public reason. In the second part of the paper, I try to show that the argument from the limitations of human cognition fails to get AI off the hook of public reason. Against a growing trend in AI ethics, my main argument is that the analogy between human minds and artificial neural networks fails because it suffers from an atomistic bias which makes it blind to the social and institutional dimension of human reasoning processes. I suggest that developing interpretive AI algorithms is not the only possible answer to the explainability problem; social and institutional answers are also available and in many cases more trustworthy than techno-scientific ones. (shrink)

The increased presence of medical AI in clinical use raises the ethical question which standard of explainability is required for an acceptable and responsible implementation of AI-based applications in medical contexts. In this paper, we elaborate on the emerging debate surrounding the standards of explainability for medical AI. For this, we first distinguish several goods explainability is usually considered to contribute to the use of AI in general, and medical AI in specific. Second, we propose to understand the value of (...) explainability relative to other available norms of explainable decision-making. Third, in pointing out that we usually accept heuristics and uses of bounded rationality for medical decision-making by physicians, we argue that the explainability of medical decisions should not be measured against an idealized diagnostic process, but according to practical considerations. We conclude, fourth, to resolve the issue of explainability-standards by relocating the issue to the AI’s certifiability and interpretability. (shrink)

Implicit stochastic models, including both ‘deep neural networks’ (dNNs) and the more recent unsupervised foundational models, cannot be explained. That is, it cannot be determined how they work, because the interactions of the millions or billions of terms that are contained in their equations cannot be captured in the form of a causal model. Because users of stochastic AI systems would like to understand how they operate in order to be able to use them safely and reliably, there has emerged (...) a new field called ‘explainable AI’ (XAI). When we examine the XAI literature, however, it becomes apparent that its protagonists have redefined the term ‘explanation’ to mean something else, namely: ‘interpretation’. Interpretations are indeed sometimes possible, but we show that they give at best only a subjective understanding of how a model works. We propose an alternative to XAI, namely certified AI (CAI), and describe how an AI can be specified, realized, and tested in order to become certified. The resulting approach combines ontologies and formal logic with statistical learning to obtain reliable AI systems which can be safely used in technical applications. (shrink)

In a recent article in this journal, Baron (2025) argues that we can appropriately trust unexplainable artificial intelligence (AI) systems, so explainability is not necessary for AI’s trustworthiness. In this commentary, I argue that Baron is wrong. I first offer a positive argument for the claim that explainability is necessary for trustworthiness. Drawing on this argument, I then show that Baron’s argument for thinking otherwise fails.

AI systems are expected to impact the ways we communicate, learn, and interact with technology. However, there are still major concerns about their commonsense reasoning, and personalization. This article computationally explains causal (vs. statistical) inference, at different levels of abstraction, and provides three examples of how we can use do-operator, a mathematical operator for intervention, to address some of these concerns. The first example is from an educational module that I developed and implemented for undergraduate engineering students, as part of (...) an educational research project with the US National Science Foundation. For the first time, to the best of my knowledge, 117 students could successfully use do-operator in a cybersecurity investment decision, according to Bloom’s learning taxonomy. Gender did not make a significant difference in the students’ performance, according to the Mann–Whitney U test. The second example explains using do-operator in assessing the effectiveness of intelligent tutoring systems, ITS, in receiving higher grades. The third example sheds light on combining online learning and offline learning, in reinforcement learning, to find the optimal policy that maximizes reward. To shed light on future research on explainability and personalization, I offer two recommendations: 1- Learn like System 2, the conscious learner (based on Bengio’s proposal for deep learning 2.0), and 2- Preference, a process, not an object (based on preference analysis of 25,646 registrants, entities and individuals purchasing domain names). In conclusion, this article contributes to achieving the goal of human–AI: Machines that think that learn and that create. (shrink)

Background Despite continuous performance improvements, especially in clinical contexts, a major challenge of Artificial Intelligence based Decision Support Systems (AI-DSS) remains their degree of epistemic opacity. The conditions of and the solutions for the justified use of the occasionally unexplainable technology in healthcare are an active field of research. In March 2024, the European Union agreed upon the Artificial Intelligence Act (AIA), requiring medical AI-DSS to be ad-hoc explainable or to use post-hoc explainability methods. The ethical debate does not (...) seem to settle on this requirement yet. This systematic review aims to outline and categorize the positions and arguments in the ethical debate. Methods We conducted a literature search on PubMed, BASE, and Scopus for English-speaking scientific peer-reviewed publications from 2016 to 2024. The inclusion criterion was to give explicit requirements of explainability for AI-DSS in healthcare and reason for it. Non-domain-specific documents, as well as surveys, reviews, and meta-analyses were excluded. The ethical requirements for explainability outlined in the documents were qualitatively analyzed with respect to arguments for the requirement of explainability and the required level of explainability. Results The literature search resulted in 1662 documents; 44 documents were included in the review after eligibility screening of the remaining full texts. Our analysis showed that 17 records argue in favor of the requirement of explainable AI methods (xAI) or ad-hoc explainable models, providing 9 categories of arguments. The other 27 records argued against a general requirement, providing 11 categories of arguments. Also, we found that 14 works advocate the need for context-dependent levels of explainability, as opposed to 30 documents, arguing for context-independent, absolute standards. Conclusions The systematic review of reasons shows no clear agreement on the requirement of post-hoc explainability methods or ad-hoc explainable models for AI-DSS in healthcare. The arguments found in the debate were referenced and responded to from different perspectives, demonstrating an interactive discourse. Policymakers and researchers should watch the development of the debate closely. Conversely, ethicists should be well informed by empirical and technical research, given the frequency of advancements in the field. (shrink)

As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from (...) diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders. (shrink)

The increasing application of artificial intelligence (AI) to healthcare raises both hope and ethical concerns. Some advanced machine learning methods provide accurate clinical predictions at the expense of a significant lack of explainability. Alex John London has defended that accuracy is a more important value than explainability in AI medicine. In this article, we locate the trade-off between accurate performance and explainable algorithms in the context of distributive justice. We acknowledge that accuracy is cardinal from outcome-oriented justice because it (...) helps to maximize patients’ benefits and optimizes limited resources. However, we claim that the opaqueness of the algorithmic black box and its absence of explainability threatens core commitments of procedural fairness such as accountability, avoidance of bias, and transparency. To illustrate this, we discuss liver transplantation as a case of critical medical resources in which the lack of explainability in AI-based allocation algorithms is procedurally unfair. Finally, we provide a number of ethical recommendations for when considering the use of unexplainable algorithms in the distribution of health-related resources. (shrink)

A major challenge with the increasing use of Artificial Intelligence applications is to manage the long-term societal impacts of this technology. Two central concerns that have emerged in this respect are that the optimized goals behind the data processing of AI applications usually remain opaque and the energy footprint of their data processing is growing quickly. This study thus explores how much people value the transparency and environmental sustainability of AI using the example of personal AI assistants. The results from (...) a choice-based conjoint analysis with a sample of more than 1.000 respondents from Germany indicate that people hardly care about the energy efficiency of AI; and while they do value transparency through explainable AI, this added value of an application is offset by minor costs. The findings shed light on what kinds of AI people are likely to demand and have important implications for policy and regulation. (shrink)

It is frequently demanded that AI-based Decision Support Tools (AI-DSTs) ought to be both explainable to, and trusted by, those who use them. The joint pursuit of these two principles is ordinarily believed to be uncontroversial. In fact, a common view is that AI systems should be made explainable so that they can be trusted, and in turn, accepted by decision-makers. However, the moral scope of these two principles extends far beyond this particular instrumental connection. This paper argues (...) that if we were to account for the rich and diverse moral reasons that ground the call for explainable AI, and fully consider what it means to “trust” AI in a descriptively rich sense of the term, we would uncover a deep and persistent tension between the two principles. For explainable AI to usefully serve the pursuit of normatively desirable goals, decision-makers must carefully monitor and critically reflect on the content of an AI-DST’s explanation. This entails a deliberative attitude. Conversely, calls for trust in AI-DSTs imply the disposition to put questions about their reliability out of mind. This entails an unquestioning attitude. As such, the joint pursuit of explainable and trusted AI calls on decision-makers to simultaneously adopt incompatible attitudes towards their AI-DST, which leads to an intractable implementation gap. We analyze this gap and explore its broader implications: suggesting that we may need alternate theoretical conceptualizations of what explainability and trust entail, and/or alternate decision-making arrangements that separate the requirements for trust and deliberation to different parties. (shrink)

With regard to current debates on the ethical implementation of AI, especially two demands are linked: the call for explainability and for ultimate human responsibility. In the medical field, both are condensed into the role of one person: It is the physician to whom AI output should be explainable and who should thus bear ultimate responsibility for diagnostic or treatment decisions that are based on such AI output. In this article, we argue that a black box AI indeed creates (...) a rationally irresolvable epistemic situation for the physician involved. Specifically, strange errors that are occasionally made by AI sometimes detach its output from human reasoning. Within this article it is further argued that such an epistemic situation is problematic in the context of ultimate human responsibility. Since said strange errors limit the promises of explainability and the concept of explainability frequently appears irrelevant or insignificant when applied to a diverse set of medical applications, we deem it worthwhile to reconsider the call for ultimate human responsibility. (shrink)

When is it justified to use opaque artificial intelligence (AI) output in medical decision-making? Consideration of this question is of central importance for the responsible use of opaque machine learning (ML) models, which have been shown to produce accurate and reliable diagnoses, prognoses, and treatment suggestions in medicine. In this article, I discuss the merits of two answers to the question. According to the Explanation View, clinicians must have access to an explanation of why an output was produced. According to (...) the Validation View, it is sufficient that the AI system has been validated using established standards for safety and reliability. I defend the Explanation View against two lines of criticism, and I argue that within the framework of evidence-based medicine mere validation seems insufficient for the use of AI output. I end by characterizing the epistemic responsibility of clinicians and point out how a mere AI output cannot in itself ground a practical conclusion about what to do. (shrink)

Purpose Along with the various beneficial uses of artificial intelligence, there are various unsavory concomitants including the inscrutability of AI tools, the fragility of AI models under adversarial settings, the vulnerability of AI models to bias throughout their pipeline, the high planetary cost of running large AI models and the emergence of exploitative surveillance capitalism-based economic logic built on AI technology. This study aims to document these harms of AI technology and study how these technologies and their developers and users (...) can be made more accountable. Design/methodology/approach Due to the nature of the problem, a holistic, multi-pronged approach is required to understand and counter these potential harms. This paper identifies the rationale for urgently focusing on human-centered AI and provide an outlook of promising directions including technical proposals. Findings AI has the potential to benefit the entire society, but there remains an increased risk for vulnerable segments of society. This paper provides a general survey of the various approaches proposed in the literature to make AI technology more accountable. This paper reports that the development of ethical accountable AI design requires the confluence and collaboration of many fields and that lack of diversity is a problem plaguing the state of the art in AI. Originality/value This paper provides a timely synthesis of the various technosocial proposals in the literature spanning technical areas such as interpretable and explainable AI; algorithmic auditability; as well as policy-making challenges and efforts that can operationalize ethical AI and help in making AI accountable. This paper also identifies and shares promising future directions of research. (shrink)

Explainable artificial intelligence (XAI) is an emerging, multidisciplinary field of research that seeks to develop methods and tools for making AI systems more explainable or interpretable. XAI researchers increasingly recognise explainability as a context-, audience- and purpose-sensitive phenomenon, rather than a single well-defined property that can be directly measured and optimised. However, since there is currently no overarching definition of explainability, this poses a risk of miscommunication between the many different researchers within this multidisciplinary space. This is the (...) problem we seek to address in this paper. We outline a framework, called Explanatory Pragmatism, which we argue has two attractive features. First, it allows us to conceptualise explainability in explicitly context-, audience- and purpose-relative terms, while retaining a unified underlying definition of explainability. Second, it makes visible any normative disagreements that may underpin conflicting claims about explainability regarding the purposes for which explanations are sought. Third, it allows us to distinguish several dimensions of AI explainability. We illustrate this framework by applying it to a case study involving a machine learning model for predicting whether patients suffering disorders of consciousness were likely to recover consciousness. (shrink)

Artificial intelligence (AI) systems have demonstrated impressive performance across a variety of clinical tasks. However, notoriously, sometimes these systems are 'black boxes'. The initial response in the literature was a demand for 'explainable AI'. However, recently, several authors have suggested that making AI more explainable or 'interpretable' is likely to be at the cost of the accuracy of these systems and that prioritising interpretability in medical AI may constitute a 'lethal prejudice'. In this paper, we defend the value (...) of interpretability in the context of the use of AI in medicine. Clinicians may prefer interpretable systems over more accurate black boxes, which in turn is sufficient to give designers of AI reason to prefer more interpretable systems in order to ensure that AI is adopted and its benefits realised. Moreover, clinicians may be justified in this preference. Achieving the downstream benefits from AI is critically dependent on how the outputs of these systems are interpreted by physicians and patients. A preference for the use of highly accurate black box AI systems, over less accurate but more interpretable systems , may itself constitute a form of lethal prejudice that may diminish the benefits of AI to - and perhaps even harm - patients. (shrink)