We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealised explanation game in which players collaborate to find the best explanation for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal (...) patterns of variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealisedexplanation gamein which players collaborate to find the best explanation(s) for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal patterns of (...) variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a (conditionally) optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

As machine learning has gradually entered into ever more sectors of public and private life, there has been a growing demand for algorithmic explainability. How can we make the predictions of complex statistical models more intelligible to end users? A subdiscipline of computer science known as interpretable machine learning (IML) has emerged to address this urgent question. Numerous influential methods have been proposed, from local linear approximations to rule lists and counterfactuals. In this article, I highlight three conceptual challenges that (...) are largely overlooked by authors in this area. I argue that the vast majority of IML algorithms are plagued by (1) ambiguity with respect to their true target; (2) a disregard for error rates and severe testing; and (3) an emphasis on product over process. Each point is developed at length, drawing on relevant debates in epistemology and philosophy of science. Examples and counterexamples from IML are considered, demonstrating how failure to acknowledge these problems can result in counterintuitive and potentially misleading explanations. Without greater care for the conceptual foundations of IML, future work in this area is doomed to repeat the same mistakes. (shrink)

Automated algorithms are silently making crucial decisions about our lives, but most of the time we have little understanding of how they work. To counter this hidden influence, there have been increasing calls for algorithmic transparency. Much ink has been spilled over the informational account of algorithmic transparency—about how much information should be revealed about the inner workings of an algorithm. But few studies question the power structure beneath the informational disclosure of the algorithm. As a result, the information disclosure (...) itself can be a means of manipulation used by a group of people to advance their own interests. Instead of concentrating on information disclosure, this paper examines algorithmic transparency from the perspective of power, explaining how algorithmic transparency under a disciplinary power structure can be a technique of normalizing people’s behavior. The informational disclosure of an algorithm can not only set up some de facto norms, but also build a scientific narrative of its algorithm to justify those norms. In doing so, people would be internally motivated to follow those norms with less critical analysis. This article suggests that we should not simply open the black box of an algorithm without challenging the existing power relations. (shrink)

Machine Learning (ML) is on the rise in medicine, promising improved diagnostic, therapeutic and prognostic clinical tools. While these technological innovations are bound to transform health care, they also bring new ethical concerns to the forefront. One particularly elusive challenge regards discriminatory algorithmic judgements based on biases inherent in the training data. A common line of reasoning distinguishes between justified differential treatments that mirror true disparities between socially salient groups, and unjustified biases which do not, leading to misdiagnosis and erroneous (...) treatment. In the curation of training data this strategy runs into severe problems though, since distinguishing between the two can be next to impossible. We thus plead for a pragmatist dealing with algorithmic bias in healthcare environments. By recurring to a recent reformulation of William James’s pragmatist understanding of truth, we recommend that, instead of aiming at a supposedly objective truth, outcome-based therapeutic usefulness should serve as the guiding principle for assessing ML applications in medicine. (shrink)

Certain characteristics make machine learning a powerful tool for processing large amounts of data, and also particularly unsuitable for explanatory purposes. There are worries that its increasing use in science may sideline the explanatory goals of research. We analyze the key characteristics of ML that might have implications for the future directions in scientific research: epistemic opacity and the ‘theory-agnostic’ modeling. These characteristics are further analyzed in a comparison of ML with the traditional statistical methods, in order to demonstrate what (...) it is specifically that makes ML methodology substantially unsuitable for reaching explanations. The analysis is given broader philosophical context by connecting it with the views on the role of prediction and explanation in science, their relationship, and the value of explanation. We proceed to show, first, that ML disrupts the relationship between prediction and explanation commonly understood as a functional relationship. Then we show that the value of explanation is not exhausted in purely predictive functions, but rather has a ubiquitously recognized value for both science and everyday life. We then invoke two hypothetical scenarios with different degrees of automatization of science, which help test our intuitions on the role of explanation in science. The main question we address is whether ML will reorient or otherwise impact our standard explanatory practice. We conclude with a prognosis that ML would diversify science into purely predictively oriented research based on ML-like techniques and, on the other hand, remaining faithful to anthropocentric research focused on the search for explanation. (shrink)

The need for fair and just AI is often related to the possibility of understanding AI itself, in other words, of turning an opaque box into a glass box, as inspectable as possible. Transparency and explainability, however, pertain to the technical domain and to philosophy of science, thus leaving the ethics and epistemology of AI largely disconnected. To remedy this, we propose an integrated approach premised on the idea that a glass-box epistemology should explicitly consider how to incorporate values and (...) other normative considerations, such as intersectoral vulnerabilities, at critical stages of the whole process from design and implementation to use and assessment. To connect ethics and epistemology of AI, we perform a double shift of focus. First, we move from trusting the output of an AI system to trusting the process that leads to the outcome. Second, we move from expert assessment to more inclusive assessment strategies, aiming to facilitate expert and non-expert assessment. Together, these two moves yield a framework usable for experts and non-experts when they inquire into relevant epistemological and ethical aspects of AI systems. We dub our framework ‘epistemology-cum-ethics’ to signal the equal importance of both aspects. We develop it from the vantage point of the designers: how to create the conditions to internalize values into the whole process of design, implementation, use, and assessment of an AI system, in which values (epistemic and non-epistemic) are explicitly considered at each stage and inspectable by every salient actor involved at any moment. (shrink)

The increasing demand for transparency in AI has recently come under scrutiny. The question is often posted in terms of “epistemic double standards”, and whether the standards for transparency in AI ought to be higher than, or equivalent to, our standards for ordinary human reasoners. I agree that the push for increased transparency in AI deserves closer examination, and that comparing these standards to our standards of transparency for other opaque systems is an appropriate starting point. I suggest that a (...) more fruitful exploration of this question will involve a different comparison class. We routinely treat judgments made by highly trained experts in specialized fields as fair or well-grounded even though—by the nature of expert/layperson division of epistemic labor—an expert will not be able to provide an explanation of the reasoning behind these judgments that makes sense to most other people. Regardless, laypeople are thought to be acting reasonably—and ethically—in deferring to the judgments of experts that concern their areas of specialization. I suggest that we reframe our question regarding the appropriate standards of transparency in AI as one that asks when, why, and to what degree it would be ethical to accept opacity in AI. I argue that our epistemic relation to certain opaque AI technology may be relevantly similar to the layperson’s epistemic relation to the expert in certain respects, such that the successful expert/layperson division of epistemic labor can serve as a blueprint for the ethical use of opaque AI. (shrink)

Autonomy is a core value that is deeply entrenched in the moral, legal, and political practices of many societies. The development and deployment of artificial intelligence (AI) have raised new questions about AI’s impacts on human autonomy. However, systematic assessments of these impacts are still rare and often held on a case-by-case basis. In this article, I provide a conceptual framework that both ties together seemingly disjoint issues about human autonomy, as well as highlights differences between them. In the first (...) part, I distinguish between distinct concerns that are currently addressed under the umbrella term ‘human autonomy’. In particular, I show how differentiating between autonomy-as-authenticity and autonomy-as-agency helps us to pinpoint separate challenges from AI deployment. Some of these challenges are already well-known (e.g. online manipulation or limitation of freedom), whereas others have received much less attention (e.g. adaptive preference formation). In the second part, I address the different roles AI systems can assume in the context of autonomy. In particular, I differentiate between AI systems taking on agential roles and AI systems being used as tools. I conclude that while there is no ‘silver bullet’ to address concerns about human autonomy, considering its various dimensions can help us to systematically address the associated risks. (shrink)

Assistive systems based on Artificial Intelligence (AI) are bound to reshape decision-making in all areas of society. One of the most intricate challenges arising from their implementation in high-stakes environments such as medicine concerns their frequently unsatisfying levels of explainability, especially in the guise of the so-called black-box problem: highly successful models based on deep learning seem to be inherently opaque, resisting comprehensive explanations. This may explain why some scholars claim that research should focus on rendering AI systems understandable, rather (...) than explainable. Yet, there is a grave lack of agreement concerning these terms in much of the literature on AI. We argue that the seminal distinction made by the philosopher and physician Karl Jaspers between different types of explaining and understanding in psychopathology can be used to promote greater conceptual clarity in the context of Machine Learning (ML). Following Jaspers, we claim that explaining and understanding constitute multi-faceted epistemic approaches that should not be seen as mutually exclusive, but rather as complementary ones as in and of themselves they are necessarily limited. Drawing on the famous example of Watson for Oncology we highlight how Jaspers’ methodology translates to the case of medical AI. Classical considerations from the philosophy of psychiatry can therefore inform a debate at the centre of current AI ethics, which in turn may be crucial for a successful implementation of ethically and legally sound AI in medicine. (shrink)

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the purpose of providing an explanation of a model or a decision is to make it understandable to its stakeholders. But without a previous grasp of what it means to say that an agent understands a model or a decision, the explanatory strategies will (...) lack a well-defined goal. Aside from providing a clearer objective for XAI, focusing on understanding also allows us to relax the factivity condition on explanation, which is impossible to fulfill in many machine learning models, and to focus instead on the pragmatic conditions that determine the best fit between a model and the methods and devices deployed to understand it. After an examination of the different types of understanding discussed in the philosophical and psychological literature, I conclude that interpretative or approximation models not only provide the best way to achieve the objectual understanding of a machine learning model, but are also a necessary condition to achieve post hoc interpretability. This conclusion is partly based on the shortcomings of the purely functionalist approach to post hoc interpretability that seems to be predominant in most recent literature. (shrink)

In many critical investigations of machine vision, the focus lies almost exclusively on dataset bias and on fixing datasets by introducing more and more diverse sets of images. We propose that machine vision systems are inherently biased not only because they rely on biased datasets but also because theirperceptual topology, their specific way of representing the visual world, gives rise to a new class of bias that we callperceptual bias. Concretely, we define perceptual topology as the set of those inductive (...) biases in machine vision systems that determine its capability to represent the visual world. Perceptual bias, then, describes the difference between the assumed “ways of seeing” of a machine vision system, our reasonable expectations regarding its way of representing the visual world, and its actual perceptual topology. We show how perceptual bias affects the interpretability of machine vision systems in particular, by means of a close reading of a visualization technique called “feature visualization”. We conclude that dataset bias and perceptual bias both need to be considered in the critical analysis of machine vision systems and propose to understand critical machine vision as an important transdisciplinary challenge, situated at the interface of computer science and visual studies/Bildwissenschaft. (shrink)

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)

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)

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)

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)

Human oversight has become a key mechanism for the governance of artificial intelligence (“AI”). Human overseers are supposed to increase the accuracy and safety of AI systems, uphold human values, and build trust in the technology. Empirical research suggests, however, that humans are not reliable in fulfilling their oversight tasks. They may be lacking in competence or be harmfully incentivised. This creates a challenge for human oversight to be effective. In addressing this challenge, this article aims to make three contributions. (...) First, it surveys the emerging laws of oversight, most importantly the European Union’s Artificial Intelligence Act (“AIA”). It will be shown that while the AIA is concerned with the competence of human overseers, it does not provide much guidance on how to achieve effective oversight and leaves oversight obligations for AI developers underdefined. Second, this article presents a novel taxonomy of human oversight roles, differentiated along whether human intervention is constitutive to, or corrective of a decision made or supported by an AI. The taxonomy allows to propose suggestions for improving effectiveness tailored to the type of oversight in question. Third, drawing on scholarship within democratic theory, this article formulates six normative principles which institutionalise distrust in human oversight of AI. The institutionalisation of distrust has historically been practised in democratic governance. Applied for the first time to AI governance, the principles anticipate the fallibility of human overseers and seek to mitigate them at the level of institutional design. They aim to directly increase the trustworthiness of human oversight and to indirectly inspire well-placed trust in AI governance. (shrink)

Previous research in Explainable Artificial Intelligence (XAI) suggests that a main aim of explainability approaches is to satisfy specific interests, goals, expectations, needs, and demands regarding artificial systems (we call these “stakeholders' desiderata”) in a variety of contexts. However, the literature on XAI is vast, spreads out across multiple largely disconnected disciplines, and it often remains unclear how explainability approaches are supposed to achieve the goal of satisfying stakeholders' desiderata. This paper discusses the main classes of stakeholders calling for explainability (...) of artificial systems and reviews their desiderata. We provide a model that explicitly spells out the main concepts and relations necessary to consider and investigate when evaluating, adjusting, choosing, and developing explainability approaches that aim to satisfy stakeholders' desiderata. This model can serve researchers from the variety of different disciplines involved in XAI as a common ground. It emphasizes where there is interdisciplinary potential in the evaluation and the development of explainability approaches. (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)

A large part of the explainable AI literature focuses on what explanations are in general, what algorithmic explainability is more specifically, and how to code these principles of explainability into AI systems. Much less attention has been devoted to the question of why algorithmic decisions and systems should be explainable and whether there ought to be a right to explanation and why. We therefore explore the normative landscape of the need for AI to be explainable and individuals having a right (...) to such explanation. This exploration is particularly relevant to the medical domain where the (im)possibility of explainable AI is high on both the research and practitioners’ agenda. The dominant intuition overall is that explainability has and should play a key role in the health context. Notwithstanding the strong normative intuition for having a right to explanation, intuitions can be wrong. So, we need more than an appeal to intuitions when it comes to explaining the normative significance of having a right to explanation when being subject to AI-based decision-making. The aim of the paper is therefore to provide an account of what might underlie the normative intuition. We defend the ‘symmetry thesis’ according to which there is no special normative reason to have a right to explanation when ‘machines’ in the broad sense, make decisions, recommend treatment, discover tumors, and so on. Instead, we argue that we have a right to explanation in cases that involve automated processing that significantly affect our core deliberative agency and which we do not understand, because we have a general moral right to explanation when choices are made which significantly affect us but which we do not understand. (shrink)

This paper explores the role and resolution of disagreements between physicians and their diagnostic AI-based decision support systems. With an ever-growing number of applications for these independently operating diagnostic tools, it becomes less and less clear what a physician ought to do in case their diagnosis is in faultless conflict with the results of the DSS. The consequences of such uncertainty can ultimately lead to effects detrimental to the intended purpose of such machines, e.g. by shifting the burden of proof (...) towards a physician. Thus, we require normative clarity for integrating these machines without affecting established, trusted, and relied upon workflows. In reconstructing different causes of conflicts between physicians and their AI-based tools—inspired by the approach of “meaningful human control” over autonomous systems and the challenges to resolve them—we will delineate normative conditions for “meaningful disagreements”. These incorporate the potential of DSS to take on more tasks and outline how the moral responsibility of a physician can be preserved in an increasingly automated clinical work environment. (shrink)

The paper explores some normative challenges concerning the integration of Machine Learning (ML) algorithms into anticorruption in public institutions. The challenges emerge from the tensions between an approach treating ML algorithms as allies to an exclusively legalistic conception of anticorruption and an approach seeing them within an institutional ethics of office accountability. We explore two main challenges. One concerns the variable opacity of some ML algorithms, which may affect public officeholders’ capacity to account for institutional processes relying upon ML techniques. (...) The other pinpoints the risk that automating certain institutional processes may weaken officeholders’ direct engagement to take forward-looking responsibility for the working of their institution. We discuss why both challenges matter to see how ML algorithms may enhance (and not hinder) institutional answerability practices. (shrink)

Despite the increase in the research field of ethics in artificial intelligence, most efforts have focused on the debate about principles and guidelines for responsible AI, but not enough attention has been given to the “how” of applied ethics. This paper aims to advance the research exploring the gap between practice and principles in AI ethics by identifying how companies are applying those guidelines and principles in practice. Through a qualitative methodology based on 22 semi-structured interviews and two focus groups, (...) the goal of the current study is to understand how companies approach ethical issues related to AI systems. A structured analysis of the transcripts brought out many actual practices and findings, which are presented around the following main research topics: ethics and principles, privacy, explainability, and fairness. The interviewees also raised issues of accountability and governance. Finally, some recommendations are suggested such as developing specific sector regulations, fostering a data-driven organisational culture, considering the algorithm’s complete life cycle, developing and using a specific code of ethics, and providing specific training on ethical issues. Despite some obvious limitations, such as the type and number of companies interviewed, this work identifies real examples and direct priorities to advance the research exploring the gap between practice and principles in AI ethics, with a specific focus on Spanish companies. (shrink)

The paper presents an ethical analysis and constructive critique of the current practice of AI ethics. It identifies conceptual substantive and procedural challenges and it outlines strategies to address them. The strategies include countering the hype and understanding AI as ubiquitous infrastructure including neglected issues of ethics and justice such as structural background injustices into the scope of AI ethics and making the procedures and fora of AI ethics more inclusive and better informed with regard to philosophical ethics. These measures (...) integrate the perspective of AI justice into AI ethics, strengthening its capacity to provide comprehensive normative orientation and guidance for the development and use of AI that actually improves human lives and living together. (shrink)

Current advances in research, development and application of artificial intelligence systems have yielded a far-reaching discourse on AI ethics. In consequence, a number of ethics guidelines have been released in recent years. These guidelines comprise normative principles and recommendations aimed to harness the “disruptive” potentials of new AI technologies. Designed as a semi-systematic evaluation, this paper analyzes and compares 22 guidelines, highlighting overlaps but also omissions. As a result, I give a detailed overview of the field of AI ethics. Finally, (...) I also examine to what extent the respective ethical principles and values are implemented in the practice of research, development and application of AI systems—and how the effectiveness in the demands of AI ethics can be improved. (shrink)

Machine behavior that is based on learning algorithms can be significantly influenced by the exposure to data of different qualities. Up to now, those qualities are solely measured in technical terms, but not in ethical ones, despite the significant role of training and annotation data in supervised machine learning. This is the first study to fill this gap by describing new dimensions of data quality for supervised machine learning applications. Based on the rationale that different social and psychological backgrounds of (...) individuals correlate in practice with different modes of human–computer-interaction, the paper describes from an ethical perspective how varying qualities of behavioral data that individuals leave behind while using digital technologies have socially relevant ramification for the development of machine learning applications. The specific objective of this study is to describe how training data can be selected according to ethical assessments of the behavior it originates from, establishing an innovative filter regime to transition from the big data rationale n = all to a more selective way of processing data for training sets in machine learning. The overarching aim of this research is to promote methods for achieving beneficial machine learning applications that could be widely useful for industry as well as academia. (shrink)

The current “AI Summer” is marked by scientific breakthroughs and economic successes in the fields of research, development, and application of systems with artificial intelligence. But, aside from the great hopes and promises associated with artificial intelligence, there are a number of challenges, shortcomings and even limitations of the technology. For one, these challenges arise from methodological and epistemological misconceptions about the capabilities of artificial intelligence. Secondly, they result from restrictions of the social context in which the development of applications (...) of machine learning is embedded. And third, they are a consequence of current technical limitations in the development and use of artificial intelligence. The paper intends to provide an overview of current challenges which the research and development of applications in the field of artificial intelligence and machine learning have to face, whereas all three mentioned areas are to be further explored in this paper. (shrink)

In this paper, we argue that one way to approach what is known in the literature as the “Trust Gap” in Medical AI is to focus on explanations from an Explainable AI (xAI) perspective. Against the current framework on xAI – which does not offer a real solution – we argue for a pragmatist turn, one that focuses on understanding how we provide explanations in Traditional Medicine (TM), composed by human agents only. Following this, explanations have two specific relevant components: (...) they are usually (i) social and (ii) abductive. Explanations, in this sense, ought to provide understanding by answering contrastive _why-questions_: “Why had P happened instead of Q?” (Miller in AI 267:1–38, 2019) (Sect. 1 ). In order to test the relevancy of this concept of explanation in medical xAI, we offer several reasons to argue that abductions are crucial for medical reasoning and provide a crucial tool to deal with trust gaps between human agents (Sect. 2 ). If abductions are relevant in TM, we can test the capability of Artificial Intelligence systems on this merit. Therefore, we provide an analysis of the capacity for social and abductive reasoning of different AI technologies. Accordingly, we posit that Large Language Models (LLMs) and transformer architectures exhibit a noteworthy potential for effective engagement in abductive reasoning. By leveraging the potential abductive capabilities of LLMs and transformers, we anticipate a paradigm shift in the integration of explanations within AI systems. This, in turn, has the potential to enhance the trustworthiness of AI-driven medical decisions, bridging the Trust Gap that has been a prominent challenge in the field of Medical AI (Sect. 3 ). This development holds the potential to not only improve the interpretability of AI-generated medical insights but also to guarantee that trust among practitioners, patients, and stakeholders in the healthcare domain is still present. (shrink)

We argue that artificial networks are explainable and offer a novel theory of interpretability. Two sets of conceptual questions are prominent in theoretical engagements with artificial neural networks, especially in the context of medical artificial intelligence: Are networks explainable, and if so, what does it mean to explain the output of a network? And what does it mean for a network to be interpretable? We argue that accounts of “explanation” tailored specifically to neural networks have ineffectively reinvented the wheel. In (...) response to, we show how four familiar accounts of explanation apply to neural networks as they would to any scientific phenomenon. We diagnose the confusion about explaining neural networks within the machine learning literature as an equivocation on “explainability,” “understandability” and “interpretability.” To remedy this, we distinguish between these notions, and answer by offering a theory and typology of interpretation in machine learning. Interpretation is something one does to an explanation with the aim of producing another, more understandable, explanation. As with explanation, there are various concepts and methods involved in interpretation: Total or Partial, Global or Local, and Approximative or Isomorphic. Our account of “interpretability” is consistent with uses in the machine learning literature, in keeping with the philosophy of explanation and understanding, and pays special attention to medical artificial intelligence systems. (shrink)

Algorithmic decision-making based on profiling may significantly affect people’s destinies. As a rule, however, explanations for such decisions are lacking. What are the chances for a “right to explanation” to be realized soon? After an exploration of the regulatory efforts that are currently pushing for such a right it is concluded that, at the moment, the GDPR stands out as the main force to be reckoned with. In cases of profiling, data subjects are granted the right to receive meaningful information (...) about the functionality of the system in use; for fully automated profiling decisions even an explanation has to be given. However, the trade secrets and intellectual property rights (IPRs) involved must be respected as well. These conflicting rights must be balanced against each other; what will be the outcome? Looking back to 1995, when a similar kind of balancing had been decreed in Europe concerning the right of access (DPD), Wachter et al. (2017) find that according to judicial opinion only generalities of the algorithm had to be disclosed, not specific details. This hardly augurs well for a future right of access let alone to explanation. Thereupon the landscape of IPRs for machine learning (ML) is analysed. Spurred by new USPTO guidelines that clarify when inventions are eligible to be patented, the number of patent applications in the US related to ML in general, and to “predictive analytics” in particular, has soared since 2010—and Europe has followed. I conjecture that in such a climate of intensified protection of intellectual property, companies may legitimately claim that the more their application combines several ML assets that, in addition, are useful in multiple sectors, the more value is at stake when confronted with a call for explanation by data subjects. Consequently, the right to explanation may be severely crippled. (shrink)

Despite the widespread use of automated decision-making (ADM) systems, they are often developed without involving the public or those directly affected, leading to concerns about systematic biases that may perpetuate structural injustices. Existing formal fairness approaches primarily focus on statistical outcomes across demographic groups or individual fairness, yet these methods reveal ambiguities and limitations in addressing fairness comprehensively. This paper argues for a holistic approach to algorithmic fairness that integrates procedural fairness, considering both decision-making processes and their outcomes. Procedural fairness (...) emphasizes the importance of fair decision-making procedures, which aligns with theories of relational justice that stress the quality of social relations and power dynamics. We highlight the need for substantive procedural fairness to ensure better outcomes and address forward-looking responsibilities. Additionally, we propose leveraging Public Engagement, a core dimension within the well-established Responsible Research and Innovation framework, to enhance procedural fairness in ADM systems. Our contribution underscores the value of Public Engagement in fostering fairer ADM processes, thereby expanding the current focus beyond technical outcome-based approaches to encompass broader procedural considerations. (shrink)

Without doctors being able to explain medical decisions to patients, I argue their use of black box AIs would erode the effective and respectful care they provide patients. In addition, I argue that physicians should use AI black boxes only for patients in dire straits, or when physicians use AI as a “co-pilot” (analogous to a spellchecker) but can independently confirm its accuracy. I respond to A.J. London’s objection that physicians already prescribe some drugs without knowing why they work.

Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.

We argue that the trend toward providing users with feasible and actionable explanations of AI decisions—known as recourse explanations—comes with ethical downsides. Specifically, we argue that recourse explanations face several conceptual pitfalls and can lead to problematic explanation hacking, which undermines their ethical status. As an alternative, we advocate that explanations of AI decisions should aim at understanding.

While the technologies that enable Artificial Intelligence (AI) continue to advance rapidly, there are increasing promises regarding AI’s beneficial outputs and concerns about the challenges of human–computer interaction in healthcare. To address these concerns, institutions have increasingly resorted to publishing AI guidelines for healthcare, aiming to align AI with ethical practices. However, guidelines as a form of written language can be analyzed to recognize the reciprocal links between its textual communication and underlying societal ideas. From this perspective, we conducted a (...) discourse analysis to understand how these guidelines construct, articulate, and frame ethics for AI in healthcare. We included eight guidelines and identified three prevalent and interwoven discourses: (1) AI is unavoidable and desirable; (2) AI needs to be guided with (some forms of) principles (3) trust in AI is instrumental and primary. These discourses signal an over-spillage of technical ideals to AI ethics, such as over-optimism and resulting hyper-criticism. This research provides insights into the underlying ideas present in AI guidelines and how guidelines influence the practice and alignment of AI with ethical, legal, and societal values expected to shape AI in healthcare. (shrink)

I argue that, given the way that AI models work and the way that ordinary human rationality works, it is very likely that people are anthropomorphizing AI, with potentially serious consequences. There are good reasons to doubt that LLMs have anything like human understanding, and even if they have representations or meaningful contents in some sense, these are unlikely to correspond to our ordinary understanding of natural language. However, there are natural, and in some ways quite rational, pressures to anthropomorphize (...) or personify LLMs and other AI systems in biased ways. This includes not only the classical or obvious ways of personifying AI — taking them to be sentient or have consciousness and understanding — but also taking AI to simulate or function like understanding, track the meaning of our language and our reasoning or logic, or have a model of the world our language is about. These more subtle or unobvious forms of anthropomorphism or personification can contribute to automation bias, AI Hype, and all their attendant risks, and encourage stronger anthropomorphisms as multi-modal AI assistants are developed further. (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 mathéma- tique 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 et ceux de sortie. Après avoir proposé une clarification et une adaptation des notions d’inter- prétabilité et d’explicabilité telles qu’on les rencontre dans la littérature déjà abondante sur le sujet, 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)

The AI Robotics Ethics Society (AIRES) is a non-profit organization founded in 2018 by Aaron Hui to promote awareness and the importance of ethical implementation and regulation of AI. AIRES is now an organization with chapters at universities such as UCLA (Los Angeles), USC (University of Southern California), Caltech (California Institute of Technology), Stanford University, Cornell University, Brown University, and the Pontifical Catholic University of Rio Grande do Sul (Brazil). AIRES at PUCRS is the first international chapter of AIRES, and (...) as such, we are committed to promoting and enhancing the AIRES Mission. Our mission is to focus on educating the AI leaders of tomorrow in ethical principles to ensure that AI is created ethically and responsibly. As there are still few proposals for how we should implement ethical principles and normative guidelines in the practice of AI system development, the goal of this work is to try to bridge this gap between discourse and praxis. Between abstract principles and technical implementation. In this work, we seek to introduce the reader to the topic of AI Ethics and Safety. At the same time, we present several tools to help developers of intelligent systems develop "good" models. This work is a developing guide published in English and Portuguese. Contributions and suggestions are welcome. (shrink)

We argue that while digital health technologies (e.g. artificial intelligence, smartphones, and virtual reality) present significant opportunities for improving the delivery of healthcare, key concepts that are used to evaluate and understand their impact can obscure significant ethical issues related to patient engagement and experience. Specifically, we focus on the concept of empowerment and ask whether it is adequate for addressing some significant ethical concerns that relate to digital health technologies for mental healthcare. We frame these concerns using five key (...) ethical principles for AI ethics (i.e. autonomy, beneficence, non-maleficence, justice, and explicability), which have their roots in the bioethical literature, in order to critically evaluate the role that digital health technologies will have in the future of digital healthcare. (shrink)

A AI Robotics Ethics Society (AIRES) é uma organização sem fins lucrativos fundada em 2018 por Aaron Hui, com o objetivo de se promover a conscientização e a importância da implementação e regulamentação ética da AI. A AIRES é hoje uma organização com capítulos em universidade como UCLA (Los Angeles), USC (University of Southern California), Caltech (California Institute of Technology), Stanford University, Cornell University, Brown University e a Pontifícia Universidade Católica do Rio Grande do Sul (Brasil). AIRES na PUCRS é (...) o primeiro capítulo internacional da AIRES, e como tal, estamos empenhados em promover e aprimorar a Missão AIRES. Nossa missão é focar na educação dos líderes da IA de amanhã em princípios éticos, para assegurar que a IA seja criada de forma ética e responsável. Como ainda existem poucas propostas de como devemos implementar princípios éticos e diretrizes normativas na prática do desenvolvimento de sistemas de IA, o objetivo deste trabalho é tentar diminuir esta lacuna entre o discurso e a práxis. Entre princípios abstratos e implementação técnica. Neste trabalho, buscamos introduzir o leitor ao tema da Ética e Segurança da IA. Ao mesmo tempo, apresentamos uma série de ferramentas para auxiliar desenvolvedores de sistemas inteligentes a desenvolver “bons” modelos. Este trabalho é um guia em desenvolvimento publicado em inglês e português. Contribuições e sugestões são bem vindas. (shrink)

What does Cyberpunk and AI Ethics have to do with each other? Cyberpunk is a sub-genre of science fiction that explores the post-human relationships between human experience and technology. One similarity between AI Ethics and Cyberpunk literature is that both seek a dialogue in which the reader may inquire about the future and the ethical and social problems that our technological advance may bring upon society. In recent years, an increasing number of ethical matters involving AI have been pointed and (...) debated, and several ethical principles and guides have been suggested as governance policies for the tech industry. However, would this be the role of AI Ethics? To serve as a soft and ambiguous version of the law? I would like to promote in this article a more Cyberpunk way of doing AI Ethics, whit a more anarchic way of governance. In this study, I will seek to expose some of the deficits of the underlying power structures of our society, and suggest that AI governance be subject to public opinion, so that ‘good AI’ can become ‘good AI for all’. (shrink)