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. (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)

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)

Large language models (LLMs) such as ChatGPT present immense opportunities, but without proper training for users (and potentially oversight), they carry risks of misuse as well. We argue that current approaches focusing predominantly on transparency and explainability fall short in addressing the diverse needs and concerns of various user groups. We highlight the limitations of existing methodologies and propose a framework anchored on user-centric guidelines. In particular, we argue that LLM users should be given guidelines on what tasks LLMs (...) can do well and which they cannot, which tasks require further guidance or refinement by the user, and context-specific heuristics. We further argue that (some) users should be taught to refine and elaborate adequate prompts, be provided with good procedures for prompt iteration, and be taught efficient ways to verify outputs. We suggest that for users, shifting away from looking at the technology itself, but rather looking at the usage of it within contextualized sociotechnical systems, can help solve many issues related to LLMs. We further emphasize the role of real-world case studies in shaping these guidelines, ensuring they are grounded in practical, applicable strategies. Like any technology, risks of misuse can be managed through education, regulation, and responsible development. (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)

This paper discusses the problem of responsibility attribution raised by the use of artificial intelligence technologies. It is assumed that only humans can be responsible agents; yet this alone already raises many issues, which are discussed starting from two Aristotelian conditions for responsibility. Next to the well-known problem of many hands, the issue of “many things” is identified and the temporal dimension is emphasized when it comes to the control condition. Special attention is given to the epistemic condition, which draws (...) attention to the issues of transparency and explainability. In contrast to standard discussions, however, it is then argued that this knowledge problem regarding agents of responsibility is linked to the other side of the responsibility relation: the addressees or “patients” of responsibility, who may demand reasons for actions and decisions made by using AI. Inspired by a relational approach, responsibility as answerability thus offers an important additional, if not primary, justification for explainability based, not on agency, but on patiency. (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)

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)

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)

Providing healthcare services frequently involves cognitively demanding tasks, including diagnoses and analyses as well as complex decisions about treatments and therapy. From a global perspective, ethically significant inequalities exist between regions where the expert knowledge required for these tasks is scarce or abundant. One possible strategy to diminish such inequalities and increase healthcare opportunities in expert-scarce settings is to provide healthcare solutions involving digital technologies that do not necessarily require the presence of a human expert, e.g., in the form of (...) artificial intelligent decision-support systems (AI-DSS). Such algorithmic decision-making, however, is mostly developed in resource- and expert-abundant settings to support healthcare experts in their work. As a practical consequence, the normative standards and requirements for such algorithmic decision-making in healthcare require the technology to be at least as explainable as the decisions made by the experts themselves. The goal of providing healthcare in settings where resources and expertise are scarce might come with a normative pull to lower the normative standards of using digital technologies in order to provide at least some healthcare in the first place. We scrutinize this tendency to lower standards in particular settings from a normative perspective, distinguish between different types of absolute and relative, local and global standards of explainability, and conclude by defending an ambitious and practicable standard of local relative explainability. (shrink)

Goodman published his "riddle" in the middle of the 20th century and many philosophers have attempted to solve it. These attempts almost all shared an assumption that, I shall argue, might be wrong, namely, the assumption that when we project from cases we have examined to cases we have not, what we project are predicates. I shall argue that this assumption, shared by almost all attempts at a solution, looks wrong, because, in the first place, what we project are generalizations (...) and not predicates, and a generalization is projectible relative to a given context. In this paper I develop the idea of explainable-projectible generalizations versus unexplainable-unprojectible generalizations, relative to a specific context. My main claim is that we rationally project a generalization if and only if we rationally believe that there is something that explains the general phenomenon that the generalized statement in question asserts to obtain, and that a generalization is projectible, if and only if its putative truth can be explained, whether we know that it can be or not. (shrink)

Although decision‐making algorithms are not new to medicine, the availability of vast stores of medical data, gains in computing power, and breakthroughs in machine learning are accelerating the pace of their development, expanding the range of questions they can address, and increasing their predictive power. In many cases, however, the most powerful machine learning techniques purchase diagnostic or predictive accuracy at the expense of our ability to access “the knowledge within the machine.” Without an explanation in terms of reasons or (...) a rationale for particular decisions in individual cases, some commentators regard ceding medical decision‐making to black box systems as contravening the profound moral responsibilities of clinicians. I argue, however, that opaque decisions are more common in medicine than critics realize. Moreover, as Aristotle noted over two millennia ago, when our knowledge of causal systems is incomplete and precarious—as it often is in medicine—the ability to explain how results are produced can be less important than the ability to produce such results and empirically verify their accuracy. (shrink)

Machine learning systems are making considerable inroads in society owing to their ability to recognize and predict patterns. However, the decision-making logic of some widely used machine learning models, such as deep neural networks, is characterized by opacity, thereby rendering them exceedingly difficult for humans to understand and explain and, as a result, potentially risky to use. Considering the importance of addressing this opacity, this paper calls for research that studies empirically and theoretically how machine learning experts and users seek (...) to attain machine learning explainability. Focusing on automated trading, we take steps in this direction by analyzing a trading firm’s quest for explaining its deep neural network system’s actionable predictions. We demonstrate that this explainability effort involves a particular form of human–machine interaction that contains both anthropomorphic and technomorphic elements. We discuss this attempt to attain machine learning explainability in light of reflections on cross-species companionship and consider it an example of human–machine companionship. (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)

Can phenomenal consciousness be given a reductive natural explanation? Many people argue not. They claim that there is an 'explanatory gap' between physical and/or intentional states and processes, on the one hand, and phenomenal consciousness, on the other. I reply that, since we have purely recognitional concepts of experience, there is indeed a sort of gap at the level of concepts; but this need not mean that the properties picked out by those concepts are inexplicable. I show how dispositionalist higher-order (...) thought (HOT) theory can reductively explain the subjective feel of experience by deploying a form of 'consumer semantics'. First-order perceptual contents become transformed, acquiring a dimension of subjectivity, by virtue to their availability to a mind-reading (HOT generating) consumer system. (shrink)

Aaron Sloman; IV—Explaining Logical Necessity1, Proceedings of the Aristotelian Society, Volume 69, Issue 1, 1 June 1969, Pages 33–50, https://doi.org/10.1093/a.

Experimental philosophy studies show that ordinary people have conflicting moral intuitions: when asked about events in a deterministic universe, respondents exhibit compatibilist intuitions about vignettes describing concrete actions, but they have incompatibilist intuitions in response to more abstract queries. Nichols and Knobe maintain that concrete compatibilist intuitions should be explained as emotion-induced performance errors in the psychological process of moral judgment. Their theory is criticized in two main ways. First, they fail to establish that the role of emotion in generating (...) compatibilist intuitions justifies the charge of performance error. Second, doubts are raised about the reliability of the psychological processes that generate incompatibilist intuitions. (shrink)

This article has called past studies into question as they relate to describing and explaining the impact of information on policy-making. More specifically, it attempts to empirically investigate the causality of the factors involved in the impact of information on governmental decision-making. Based on an integrated conceptual framework for when and how information helps to make policy decisions, a path model (or a covariance structure model without latent variables) is built and tested against the data in two areas of mental (...) health policy (i.e., service provision and financing). Findings of the study demonstrate that how and when information influences governmental decision-making is directly and indirectly affected by a variety of factors and their linkages, not dominated by one set of factors (e.g., trustworthiness of information source or format of reports) defined by a single perspective (e.g., the organizational interest or the communications perspective). The most important paths in the model are those between factors related to information (e.g., the amount of information received or its use) and the impact of information on policy-making. Interestingly, these factors also play a major role in linking other variables (e.g., demographics or decision makers’ distrust of information) to the impact of information on policy-making. Furthermore, the general pattern of the findings indicates that policy areas make a difference in accounting for the impact of information on policy-making. Overall, the single most important lesson is that past perspectives are not alternative or competing tools for understanding the phenomena, and, thus, the theoretical and/or empirical task of explaining when and why information affects policy-making is equivalent to explaining why a certain set of factors is not appropriate or appropriate for a particular context and to identifying such a context. (shrink)

Philosophers of science have devoted volumes to the question of explanation; I've devoted some pages to it myself. In this highly contracted essay I shall offer no more than a comment on the problem of explanation, some vagrant but critical assessments of the dominant approaches to it, and a caution lest we take comfort in some of the recent "success"—or alleged success—in Psychology. I begin with this question: What does it mean to explain an occurrence? And then: What is it (...) about any explanation that makes it good or bad? 2012 APA, all rights reserved). (shrink)

By lopsided majorities, the U.S. Supreme Court, in a series of cases, persistently commanded the lower courts to condition the admission of proffered expert testimony on the demonstrated validity of the proponents’ claims of expertise. In at least one broad area – the so-called forensic sciences – the courts below have largely evaded the Supreme Court's holdings. This paper aims to try to explain this massive defiance by the lower courts in terms of social epistemology.

Carl F. Craver investigates what we are doing when we use neuroscience to explain what's going on in the brain. When does an explanation succeed and when does it fail? Craver offers explicit standards for successful explanation of the workings of the brain, on the basis of a systematic view about what neuroscientific explanations are.

: Jennifer Radden argues that it is impossible to imagine sensuously pain and explains this by noting that pains are sensory qualities for which there is no distinction between appearance and reality. By contrast, I argue that only basic sensuous imaginings of pain from the first person perspective are, with some qualifications, impossible. Non-basic sensuous imaginings of pain from the first person perspective are possible. I explain the extent to which imagining pain is impossible in terms of the conditions required (...) for representing the painfulness of pain. I outline some difficulties with Radden’s favoured explanation and note how imagining pains may have a role in depression and, to that extent, keep open the option that it may have a partly delusional character. Keywords: Imagination; Pain; Depression; Action; Delusion Spiegare l'impossibilità e la possibilità di immaginare il dolore Riassunto: Jennifer Radden sostiene come l’immaginazione sensoriale del dolore non sia possibile e lo motiva facendo notare come i dolori siano qualità sensoriali per cui non c’è distinzione tra apparenza e realtà. Per converso io sostengo come sia impossibile solo l’immaginazione sensibile di base del dolore dalla prospettiva della prima persona, con alcune specificazioni. L’immaginazione sensibile non di base del dolore dalla prospettiva della prima persona è possibile. Illustro fino a che punto l’immaginare il dolore è impossibile in termini di condizioni richieste per rappresentare la dolorosità del dolore. Sottolineo alcune difficoltà della spiegazione proposta da Radden e faccio notare come l’immaginare il dolore può aver un ruolo nella depressione e come, per questo, resti aperta l’opzione che il dolore possa avere in parte carattere illusorio. Parole chiave: Immaginazione; Dolore; Depressione; Azione; Illusione. (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)

To explain subjective consciousness in physical terms, one must first describewhat is subjective about consciousness. But such descriptions are experience-based or depend on authors’ intuitions. This is troubling because there are no empirical reasons to fix on any one description of subjectivity, and authors seem to have very different notions of what subjectivity is. Further, if subjectivity is to be physicalized somehow, it seems to need to be one type of physical thing and not many different sorts of physical things. (...) Taking a cue from the philosophy of science, I argue for a different methodology,one that mitigates these a priori troubles, by treating theories as models. Models are ways of working out explanations for empirically underdetermined, problematic phenomena. This allows a pluralistic and integrative approach to the literature. I offer a modified version of scientific realism as an alternative to empirically unwarranted atomistic metaphysical claims. I then develop a different methodology that avoids the difficulties in the firstplace. If there is no good reason to choose one description, I locate what is common to all the descriptions. There is a particular relativity to qualia and a particular nominal perspective to awareness more generally. If subjectivity is not just one physical aspect of the brain, it seems that any certain neurological evidence is also too specific. I argue instead that the problematic particularities of subjective consciousness can be understood in the more general, non-problematic particularities of biological organisms. From these non-controversial grounds, certain explanatory paths are generated. Iargue for a dispositional view of qualia, one that retains both biological-functional evidences and neurological variation. This allows a more reasonable “moderate relativity” about qualia. I argue for a dispositional view of a subjective perspective more generally, one that includes the neuro-mechanisms of awareness but does more. Consciousness is private so as to generate novel meanings, variable organism to organism. The actual aware perspective just is these non-conscious mental contents, which constitute the differences in how creatures “see the world”. Further, one’s perspective results in phenomenal valence, liking or disliking as a novel aspect of “what it is like”. (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)

Explaining the Cosmos is a major reinterpretation of Greek scientific thought before Socrates. Focusing on the scientific tradition of philosophy, Daniel Graham argues that Presocratic philosophy is not a mere patchwork of different schools and styles of thought. Rather, there is a discernible and unified Ionian tradition that dominates Presocratic debates. Graham rejects the common interpretation of the early Ionians as "material monists" and also the view of the later Ionians as desperately trying to save scientific philosophy from Parmenides' criticisms. (...) In Graham's view, Parmenides plays a constructive role in shaping the scientific debates of the fifth century BC. Accordingly, the history of Presocratic philosophy can be seen not as a series of dialectical failures, but rather as a series of theoretical advances that led to empirical discoveries. Indeed, the Ionian tradition can be seen as the origin of the scientific conception of the world that we still hold today. (shrink)

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)

​Imagination will remain a mystery—we will not be able to explain imagination—until we can break it into parts we already understand. Explaining Imagination is a guidebook for doing just that, where the parts are other ordinary mental states like beliefs, desires, judgments, and decisions. In different combinations and contexts, these states constitute cases of imagining. This reductive approach to imagination is at direct odds with the current orthodoxy, according to which imagination is a sui generis mental state or process—one with (...) its own inscrutable principles of operation. Explaining Imagination upends that view, showing how, on closer inspection, the imaginings at work in hypothetical reasoning, pretense, the enjoyment of fiction, and creativity are reducible to other familiar mental states—judgments, beliefs, desires, and decisions among them. Crisscrossing contemporary philosophy of mind, cognitive science, and aesthetics, Explaining Imagination argues that a clearer understanding of imagination is already well within reach. (shrink)

Explaining the behaviour of ecosystems is one of the key challenges for the biological sciences. Since 2000, new-mechanicism has been the main model to account for the nature of scientific explanation in biology. The universality of the new-mechanist view in biology has been however put into question due to the existence of explanations that account for some biological phenomena in terms of their mathematical properties (mathematical explanations). Supporters of mathematical explanation have argued that the explanation of the behaviour of ecosystems (...) is usually provided in terms of their mathematical properties, and not in mechanistic terms. They have intensively studied the explanation of the properties of ecosystems that behave following the rules of a non-random network. However, no attention has been devoted to the study of the nature of the explanation in those that form a random network. In this paper, we cover that gap by analysing the explanation of the stability behaviour of the microbiome recently elaborated by Coyte and colleagues, to determine whether it fits with the model of explanation suggested by the new-mechanist or by the defenders of mathematical explanation. Our analysis of this case study supports three theses: (1) that the explanation is not given solely in terms of mechanisms, as the new-mechanists understand the concept; (2) that the mathematical properties that describe the system play an essential explanatory role, but they do not exhaust the explanation; (3) that a non-previously identified appeal to the type of interactions that the entities in the network can exhibit, as well as their abundance, is also necessary for Coyte and colleagues’ account to be fully explanatory. From the combination of these three theses we argue for the necessity of an integrative pluralist view of the nature of behaviour explanation when this is given by appealing to the existence of a random network. (shrink)

What explains the truth of a universal generalization? Two types of explanation can be distinguished. While an ‘instance-based explanation’ proceeds via some or all instances of the generalization, a ‘generic explanation’ is independent of the instances, relying instead on completely general facts about the properties or operations involved in the generalization. This intuitive distinction is analyzed by means of a truthmaker semantics, which also sheds light on the correct logic of quantification. On the most natural version of the semantics, this (...) analysis vindicates some claims made—without a proper defense—by Michael Dummett, Solomon Feferman, and others. Where instance-based explanations are freely available, classical logic is shown to be warranted. By contrast, intuitionistic logic remains warranted regardless of what explanations are available. (shrink)

For some reason, participants hold agents more responsible for their actions when a situation is described concretely than when the situation is described abstractly. We present examples of this phenomenon, and survey some attempts to explain it. We divide these attempts into two classes: affective theories and cognitive theories. After criticizing both types of theories we advance our novel hypothesis: that people believe that whenever a norm is violated, someone is responsible for it. This belief, along with the familiar workings (...) of cognitive dissonance theory, is enough to not only explain all of the abstract/concrete paradoxes, but also explains seemingly unrelated effects, like the anthropomorphization of malfunctioning inanimate objects. (shrink)

Explaining Attitudes offers an important challenge to the dominant conception of belief found in the work of such philosophers as Dretske and Fodor. According to this dominant view beliefs, if they exist at all, are constituted by states of the brain. Lynne Rudder Baker rejects this view and replaces it with a quite different approach - practical realism. Seen from the perspective of practical realism, any argument that interprets beliefs as either brain states or states of immaterial souls is a (...) 'non-starter'. Practical realism takes beliefs to be states of the whole persons, rather like states of health. What a person believes is determined by what a person would do, say and think in various circumstances. Thus beliefs and other attitudes are interwoven into an integrated, commonsensical conception of reality. (shrink)

At the start of the 20th century the question of whether life could be explained in purely me- chanical terms was as hotly debated as the mind-body problem is today. Two factions opposed each other: Biological mechanists claimed that the properties characteristic of living organisms could be ex- plained mechanistically, in the way the behavior of a clock can be explained by the properties and the arrangement of its cogs, springs, and weights. Substantial vitalists, on the other hand, maintained that (...) the explanation envisaged by the mechanists was impossible and that one had to postulate a special nonphysical substance in order to explain life. (shrink)

Explaining Value is a selection of the best of Gilbert Harman's shorter writings in moral philosophy. The thirteen essays are divided into four sections, which focus in turn on moral relativism, values and valuing, character traits and virtue ethics, and ways of explaining aspects of morality. Harman's distinctive approach to moral philosophy has provoked much interest; this volume offers a fascinating conspectus of his most important work in the area.

In the book, I argue that the mind can be explained computationally because it is itself computational—whether it engages in mental arithmetic, parses natural language, or processes the auditory signals that allow us to experience music. All these capacities arise from complex information-processing operations of the mind. By analyzing the state of the art in cognitive science, I develop an account of computational explanation used to explain the capacities in question.

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)