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

Science is replete with falsehoods that epistemically facilitate understanding by virtue of being the very falsehoods they are. In view of this puzzling fact, some have relaxed the truth requirement on understanding. I offer a factive view of understanding that fully accommodates the puzzling fact in four steps: (i) I argue that the question how these falsehoods are related to the phenomenon to be understood and the question how they figure into the content of understanding it are independent. (ii) I (...) argue that the falsehoods do not figure into the understanding’s content by being elements of its periphery or core. (iii) Drawing lessons from case studies, I argue that the falsehoods merely enable understanding. When working with such falsehoods, only the truths we extract from them are elements of the content of our understanding. (iv) I argue that the extraction view is compatible with the thesis that falsehoods can have an epistemic value by virtue of being the very falsehoods they are. (shrink)

In this paper I argue that Artificial Intelligence and the many data science methods associated with it, such as machine learning and large language models, are first and foremost epistemic technologies. In order to establish this claim, I first argue that epistemic technologies can be conceptually and practically distinguished from other technologies in virtue of what they are designed for, what they do and how they do it. I then proceed to show that unlike other kinds of technology (_including_ other (...) epistemic technologies) AI can be uniquely positioned as an epistemic technology in that it is primarily designed, developed and deployed to be used in _epistemic contexts_ such as inquiry, it is specifically designed, developed and deployed to manipulate _epistemic content_ such as data, _and_ it is designed, developed and deployed to do so particularly through _epistemic operations_ such as prediction and analysis. As has been shown in recent work in the philosophy and ethics of AI (Alvarado, AI and Ethics, 2022a), understanding AI as an epistemic technology will also have significant implications for important debates regarding our relationship to AI technologies. This paper includes a brief overview of such implications, particularly those pertaining to explainability, opacity, trust and even epistemic harms related to AI technologies. (shrink)

Several argue that truth cannot be science’s sole epistemic goal, for it would fail to do justice to several scientific practices that advance understanding. I challenge these arguments, but only after making a small concession: science’s sole epistemic goal is not truth as such; rather, its goal is finding true answers to relevant questions. Using examples from the natural and social sciences, I then show that scientific understanding’s epistemically valuable features are either true answers to relevant questions or a means (...) thereof. (shrink)

In epistemology and philosophy of science, there has been substantial debate about truth’s relation to understanding. “Non-factivists” hold that radical departures from the truth are not always barriers to understanding; “quasi-factivists” demur. The most discussed example concerns scientists’ use of idealizations in certain derivations of the ideal gas law from statistical mechanics. Yet, these discussions have suffered from confusions about the relevant science, as well as conceptual confusions. Addressing this example, we shall argue that the ideal gas law is best (...) interpreted as favoring non-factivism about understanding, but only after delving a bit deeper into the statistical mechanics that has informed these arguments and stating more precisely what non-factivism entails. Along the way, we indicate where earlier discussions have gone astray, and highlight how a naturalistic approach furnishes more nuanced normative theses about the interaction of rationality, understanding, and epistemic value. (shrink)

To understand something involves some sort of commitment to a set of propositions comprising an account of the understood phenomenon. Some take this commitment to be a species of belief; others, such as Elgin and I, take it to be a kind of cognitive policy. This paper takes a step back from debates about the nature of understanding and asks when this commitment involved in understanding is epistemically appropriate, or ‘acceptable’ in Elgin’s terminology. In particular, appealing to lessons from the (...) lottery and preface paradoxes, it is argued that this type of commitment is sometimes acceptable even when it would be rational to assign arbitrarily low probabilities to the relevant propositions. This strongly suggests that the relevant type of commitment is sometimes acceptable in the absence of epistemic justification for belief, which in turn implies that understanding does not require justification in the traditional sense. The paper goes on to develop a new probabilistic model of acceptability, based on the idea that the maximally informative accounts of the understood phenomenon should be optimally probable. Interestingly, this probabilistic model ends up being similar in important ways to Elgin’s proposal to analyze the acceptability of such commitments in terms of ‘reflective equilibrium’. (shrink)

Scientific models typically contain idealizations, or assumptions that are known not to be true. Philosophers have long questioned the nature of idealizations: Are they heuristic tools that will be abandoned? Or rather fictional representations of reality? And how can we reconcile them with realism about knowledge of nature? Immanuel Kant developed an account of scientific investigation that can inspire a new approach to the contemporary debate. Kant argued that scientific investigation is possible only if guided by ideal assumptions—what he calls (...) “regulative ideas”. These ideas are not true of objects of nature, and yet they are not heuristic tools or fictional represen- tations. They are necessary rules governing the construction and assessment of scientific explanations. In this paper, I suggest that some idealizations can be interpreted as having necessary regulative value and as being compatible with scientific realism. I first analyze the puzzle of the nature of idealization and present the main approaches to this topic in the literature. Second, I reconsider the puzzle vis-a-vis a restricted, Kantian definition of idealization and a novel characterization of the relation between idealization and truth. Finally, I discuss in detail an example of idealization (the Hardy-Weinberg equilibrium) along the suggested Kantian lines. (shrink)

Scientists appeal to models when explaining phenomena. Such explanations are often dubbed model explanations or model-based explanations. But what are the precise conditions for ME? Are ME special explanations? In our paper, we first rebut two definitions of ME and specify a more promising one. Based on this analysis, we single out a related conception that is concerned with explanations that are induced from working with a model. We call them ‘model-induced explanations’. Second, we study three paradigmatic cases of alleged (...) ME. We argue that all of them are MIE, upon closer examination. Third, we argue that this undermines the building consensus that model explanations are special explanations that, e.g., challenge the factivity of explanation. Instead, it suggests that what is special about models in science is the epistemology behind how models induce explanations. (shrink)

The notion of understanding occupies an increasingly prominent place in contemporary epistemology, philosophy of science, and moral theory. A central and ongoing debate about the nature of understanding is how it relates to the truth. In a series of influential contributions, Catherine Elgin has used a variety of familiar motivations for antirealism in philosophy of science to defend a non- factive theory of understanding. Key to her position are: (i) the fact that false theories can contribute to the upwards trajectory (...) of scientific understanding, and (ii) the essential role of inaccurate idealisations in scientific research. Using Elgin’s arguments as a foil, I show that a strictly factive theory of understanding has resources with which to offer a unified response to both the problem of idealisations and the role of false theories in the upwards trajectory of scientific understanding. Hence, strictly factive theories of understanding are viable notwithstanding these forceful criticisms. (shrink)

Nietzsche offers a positive epistemology, and those who interpret him as a skeptic or a mere pragmatist are mistaken. Instead he supports what he calls per- spectivism. This is a familiar take on Nietzsche, as perspectivism has been analyzed by many previous interpreters. The present paper presents a sketch of the textually best supported and logically most consistent treatment of perspectivism as a first- order epistemic theory. What’s original in the present paper is an argument that Nietzsche also offers a (...) second-order methodological perspectivism aimed at enhancing understanding, an epistemic state distinct from knowledge. Just as Descartes considers and rejects radical skepticism while at the same time adopting methodological skepticism, one could consistently reject perspectivism as a theory of knowledge while accepting it as contributing to our understanding. It is argued that Nietzsche’s perspectivism is in fact two-tiered: knowledge is perspectival because truth itself is, and in addition there is a methodological perspectivism in which distinct ways of knowing are utilized to produce understanding. A review of the manner in which understanding is conceptualized in contemporary epistemology and philosophy of science serves to illuminate how Nietzsche was tackling these ideas. (shrink)

This chapter explores perspectivism in the American Pragmatist tradition. On the one hand, the thematization of perspectivism in contemporary epistemology and philosophy of science can benefit from resources in the American Pragmatist philosophical tradition. On the other hand, the Pragmatists have interesting and innovative, pluralistic views that can be illuminated through the lens of perspectivism. I pursue this inquiry primarily through examining relevant sources from the Pragmatist tradition. I will illustrate productive engagements between pragmatism and perspectivism in three areas: in (...) the pragmatists’ fallibilistic theories of inquiry and truth, in their pluralistic metaphysics, and in their views on cultural pluralism. While there are some potential sticking points between pragmatism and perspectivism, particularly around the visual metaphor of perspective, these philosophical approaches nonetheless have much to learn from each other. Perspectivism is in danger of falling between the horns of pernicious relativism and a platitudinous view of the limits of human perception and cognition. The pragmatists accounts of truth and reality open the possibility of a more thoroughgoing perspectivism. I will follow this thread through Charles S. Peirce’s, William James’, and John Dewey’s theories of inquiry and truth, Peirce’s evolutionary metaphysics, James’ radical pluralism, Dewey’s cultural naturalism, Richard Rorty’s anti-essentialism, Jane Addams’ standpoint epistemology, W.E.B. Du Bois’ theory of race consciousness, Horace Kallen’s and Alain LeRoy Locke’s cultural pluralism, and Mary Parker Follett’s account of pluralistic integration. (shrink)

This paper calls into question one fundamental claim at the basis of an alleged puzzle for veritistic accounts of the value of idealized models: the claim that idealized models cannot be veridical representations of the world. Catherine Elgin has argued that the value of idealized models can only be explained if we construe them as exemplars, which do not represent the world. I argue that Elgin’s proposal is problematic and cannot accommodate central cases of idealization. Nevertheless, there is value in (...) Elgin’s proposal. I rescue her notion of selectiveness in exemplification and incorporate it within a revised account of representation. I provide independent motivation in favour of a form of veritism, which motivates a revision of Elgin’s case against it. I argue that an account based on selective representation has the resources to rescue veritism from the problems raised by Elgin. In the proposal I advance, idealized models are literally veridical representations of the world. (shrink)

Relationships of counterfactual dependence have played a major role in recent debates of explanation and understanding in the philosophy of science. Usually, counterfactual dependencies have been viewed as the explanantia of explanation, i.e., the things providing explanation and understanding. Sometimes, however, counterfactual dependencies are themselves the targets of explanations in science. These kinds of explanations are the focus of this paper. I argue that “micro-level model explanations” explain the particular form of the empirical regularity underlying a counterfactual dependency by representing (...) it as a physical necessity on the basis of postulated microscopic entities. By doing so, micro-level models rule out possible forms the regularity could have taken. Micro-model explanations, in other words, constrain empirical regularities and their associated counterfactual dependencies. I introduce and illustrate micro-level model explanations in detail, contrast them to other accounts of explanation, and consider potential problems. (shrink)

Highly idealized models may serve various epistemic functions, notably explanation, in virtue of representing the world. Inferentialism provides a prima facie compelling characterization of what constitutes the representation relation. In this paper, I argue that what I call factive inferentialism does not provide a satisfactory solution to the puzzle of model-based—factive—explanation. In particular, I show that making explanatory counterfactual inferences is not a sufficient guide for accurate representation, factivity, or realism. I conclude by calling for a more explicit specification of (...) model-world mismatches and properties imputation. (shrink)

By appealing to resources found in the scientific understanding literature, I identify in what senses idealisations afford understanding in the context of the (magnetic) Aharonov-Bohm effect. Three types of concepts of understanding are discussed: understanding-what, which has to do with understanding a phenomenon; understanding-with, which has to do with understanding a scientific theory; and understanding-why, which has to do with the reason some phenomenon occurs. Consequently, I outline an account of understanding-with that is suggested by the historical controversy surrounding the (...) Aharonov-Bohm effect. (shrink)

The main purpose of this dissertation is to examine critically and discuss the role of imagination in science and religion, with particular emphasis on its possible epistemic, creative, and meaning-making functions. In order to answer my research questions, I apply theories and concepts from contemporary philosophy of mind on scientific and religious practices. This framework allows me to explore the mental state of imagination, not as an isolated phenomenon but, rather, as one of many mental states that co-exist and interplay (...) in our cogntive architecture. Based on the philosophical discourse of philosophy of mind, four types of imagination are indentified and conceptualized: sensory, propositional, experiential, and creative imagination. These categories are then employed on five phenomena that can be found in scientific and religious environments: metaphors, models, thought experiments, aspect perception, and - in the religious case - rituals. In relation to the concept of religious "seeing" I consider how imaginings may influence visionary experiences and visualization, and compare these phenomena with cases of scientific visualization and eureka experiences. In regard to scientific and religious models, a distinction is made between, on the one hand, two notions of truth and, on the other hand, truth-independent meaning-making. In light of these categories, I differentiate between, and critically discuss, the use of imagination in doxastic, non-doxastic and fictionalist accounts. In light of this investigation, I formulate and defend the position of interactivism, which acknowledges a constant interplay between different attitudes and mental states. In my examination of rituals and scientific and religious thought experiments, special attention is given to the mental capacity to recreate the experiences that are entailed in an imagined scenario. At the end of the investigation, I consider the possible impact that my study might have on how we view science and religion as well as the dialogue bewteen these two fields. (shrink)