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

We provide two programmatic frameworks for integrating philosophical research on understanding with complementary work in computer science, psychology, and neuroscience. First, philosophical theories of understanding have consequences about how agents should reason if they are to understand that can then be evaluated empirically by their concordance with findings in scientific studies of reasoning. Second, these studies use a multitude of explanations, and a philosophical theory of understanding is well suited to integrating these explanations in illuminating ways.

In this paper, we will explore one way in which understanding can—and, we will argue, should—be valuable. We will do this by drawing on what has been said about the different ways knowledge can be valuable. Our main contribution will be to identify one heretofore undiscussed way knowledge could be valuable, but isn’t—specifically, having value to someone other than the understander. We suggest that it is a desideratum on an account of understanding that understanding have the specified type of value; (...) our basis for this claim will come from recent work in cognitive psychology. This desideratum can then be used to measure the success of various accounts of understanding. We argue that accounts of understanding that have a particular structure will predict why understanding has that sort of value. For good measure, we then engage in a bit of a literature review, investigating which extant accounts of understanding satisfy this desideratum. (shrink)

Explaining phenomena is a primary goal of science. Consequently, it is unsurprising that gaining a proper understanding of the nature of explanation is an important goal of science education. In order to properly understand explanation, however, it is not enough to simply consider theories of the nature of explanation. Properly understanding explanation requires grasping the relation between explanation and understanding, as well as how explanations can lead to scientific knowledge. This article examines the nature of explanation, its relation to understanding, (...) and how explanations are used to generate scientific knowledge via inferences to the best explanation. Studying these features and applications of explanation not only provides insight into a concept that is important for science education in its own right, but also sheds light on an aspect of recent debates concerning the so-called consensus view of nature of science (NOS). Once the relation between explanation, understanding, and knowledge is clear, it becomes apparent that science is unified in important ways. Seeing this unification provides some support for thinking that there are general features of NOS of the sort proposed by the consensus view and that teaching about these general features of NOS should be a goal of science education. (shrink)

In pedagogical contexts and in everyday life, we often come to believe something because it would best explain the data. What is it about the explanatory endeavor that makes it essential to everyday learning and to scientific progress? There are at least two plausible answers. On one view, there is something special about having true explanations. This view is highly intuitive: it’s clear why true explanations might improve one’s epistemic position. However, there is another possibility—it could be that the process (...) of seeking, generating, or evaluating explanations itself puts one in a better epistemic position, even when the outcome of the process is not a true explanation. In other words, it could be that accurate explanations are beneficial, or it could be that high-quality explaining is beneficial, where there is something about the activity of looking for an explanation that improves our epistemic standing. The main goal of this paper is to tease apart these two possibilities, both theoretically and empirically, which we align with “Inference to the Best Explanation” and “Explaining for the Best Inference”, respectively. We also provide some initial support for EBI and identify promising directions for future research. (shrink)

In this article I develop a model of theoretical understanding in science. This is a philosophical theory that specifies the conditions that are both necessary and sufficient for a scientist to satisfy the construction ‘S understands theory T ’. I first consider how this construction is preferable to others, then build a model of the requisite conditions on the basis of examples from elementary physics. I then show how this model of theoretical understanding can be made philosophically robust and provide (...) a more sophisticated account than we see from models of a similar kind developed by those working in the psychology of physics and artificial intelligence. 1 Introduction2 The Explicandum/Analysandum3 Analysis of ‘S understands T’ 4 The Inferential Model4.1 Which problems are we talking about?4.2 Does the solution have to be true?4.3 Does each cycle have to be correct for S to understand T?4.4 What is problem-solving reliability?4.5 Does every specific inference of a cycle have to be correct?4.6 Does each inference have to use a principle that is part of the theory?5 Theoretical Understanding and Conceptual Expertise: Empirical Considerations6 Conclusion: Inferential Model of Scientific Understanding and Our Traditional Problems. (shrink)

The history of developmental biology is interwoven with debates as to whether mechanistic explanations of development are possible or whether alternative explanatory principles or even vital forces need to be assumed. In particular, the demonstrated ability of embryonic cells to tune their developmental fate precisely to their relative position and the overall size of the embryo was once thought to be inexplicable in mechanistic terms. Taking a causal perspective, this Element examines to what extent and how developmental biology, having turned (...) molecular about four decades ago, has been able to meet the vitalist challenge. It focuses not only on the nature of explanations but also on the usefulness of causal knowledge – including the knowledge of classical experimental embryology – for further scientific discovery. It also shows how this causal perspective allows us to understand the nature and significance of some key concepts, including organizer, signal and morphogen. This title is also available as Open Access on Cambridge Core. (shrink)

This paper connects two important debates in epistemology—to wit, on the goal of inquiry and on the nature of understanding—and offers a unified knowledge-based account of both.

This paper aims to propose an inferential and dynamic approach to understanding with models in biology. Understanding plays a central role in the practice of modeling. From its links with the other two central elements of scientific research, experimentation, and explanation, we show its epistemic relevance to the case of explanation in biology. Furthermore, by including the notion of understanding, we propose a non-referentialist perspective on scientific models, which is determined by their use.

As a strategy for exploring the relationship between understanding and knowledge, we consider whether epistemic luck – which is typically thought to undermine knowledge – undermines understanding. Questions about the etiology of understanding have also been at the heart of recent theoretical debates within epistemology. Kvanvig (2003) put forward the argument that there could be lucky understanding and produced an example that he deemed persuasive. Grimm (2006) responded with a case that, he argued, demonstrated that there could not be lucky (...) understanding. In this paper, we empirically examine how participants' patterns of understanding attributions line up with the predictions of Kvanvig and Grimm. We argue that the data challenge Kvanvig's position. People do not differentiate between knowing-why and understanding-why on the basis of proper etiology: attributions of knowledge and understanding involve comparable (and minimal) roles for epistemic luck. We thus posit that folk knowledge and understanding are etiologically symmetrical. (shrink)

Some experiences change who we are in ways we cannot understand until we have that very experience. In this paper I argue that so-called “transformative experiences” can not only bring about new understanding, but can actually be brought out by the gain of understanding itself. Coming to understand something new can change you. I argue that not only is understanding acquisition potentially a kind of transformative experience; given some of the recent philosophy of the phenomenology of understanding, it is a (...) kind that is potentially rare in not being dependent on a particular subjective phenomenology. The goal of this paper threefold. First, I argue that coming to gain cognitive understanding of an academic subject matter can, under some circumstances, itself be a transformative experience. A second, subsidiary goal of this paper is to argue that such transformative understanding merits further study. Finally, I give a rough taxonomy of under what conditions we should expect understanding acquisition to be transformative. (shrink)

In this paper, we argue that, contra Strevens (2013), understanding in the sciences is sometimes partially constituted by the possession of abilities; hence, it is not (in such cases) exhausted by the understander’s bearing a particular psychological or epistemic relationship to some set of structured propositions. Specifically, the case will be made that one does not really understand why a modeled phenomenon occurred unless one has the ability to actually work through (meaning run and grasp at each step) a model (...) simulation of the underlying dynamic. (shrink)

Scientific understanding is a fundamental goal of science. However, there is currently no good way to measure the scientific understanding of agents, whether these be humans or Artificial Intelligence systems. Without a clear benchmark, it is challenging to evaluate and compare different levels of scientific understanding. In this paper, we propose a framework to create a benchmark for scientific understanding, utilizing tools from philosophy of science. We adopt a behavioral conception of understanding, according to which genuine understanding should be recognized (...) as an ability to perform certain tasks. We extend this notion of scientific understanding by considering a set of questions that gauge different levels of scientific understanding, covering information retrieval, the capability to arrange information to produce an explanation, and the ability to infer how things would be different under different circumstances. We suggest building a Scientific Understanding Benchmark (SUB), formed by a set of these tests, allowing for the evaluation and comparison of scientific understanding. Benchmarking plays a crucial role in establishing trust, ensuring quality control, and providing a basis for performance evaluation. By aligning machine and human scientific understanding we can improve their utility, ultimately advancing scientific understanding and helping to discover new insights within machines. (shrink)

Metaphors are found all throughout science: in published papers, working hypotheses, policy documents, lecture slides, grant proposals, and press releases. They serve different functions, but perhaps most striking is the way they enable understanding, of a theory, phenomenon, or idea. In this paper, we leverage recent advances on the nature of metaphor and the nature of understanding to explore how they accomplish this feat. We attempt to shift the focus away from the epistemic value of the content of metaphors, to (...) the epistemic value of the metaphor’s consequences. Many famous scientific metaphors are epistemically good, not primarily because of what they say about the world, but because of how they cause us to think. Specifically, metaphors increase understanding either by improving our sets of representations, or by making it easier for us to encode and process data about complex subjects by changing how we are disposed to conceptualize those subjects. This view hints towards new positions concerning testimonial understanding, factivity, abilities, discovery via metaphor, and the relation between metaphors and models. (shrink)

Artificial general intelligence is not a new notion, but it has certainly been gaining traction in recent years, and academic as well as industry resources are redirected to research in AGI. The main reason for this is that current AI techniques are limited as they are designed to operate in specific problem-domains, following meticulous preparation. These systems cannot operate in an unknown environment or under conditions of uncertainty, reuse knowledge gained in another problem domain, or autonomously learn and understand the (...) problem-domain. We shall call AI systems capable of such feats artificial general intelligent systems. The three tasks of this paper are to provide a working definition of the term AGI, examine the “missing G”, i.e., the set of abilities that current AI systems lack and whose implementation will result in a basic AGI system, and consider different approaches, including a hybrid one, to a comprehensive solution for an AGI. (shrink)

While the relation between visualization and scientific understanding has been a topic of long-standing discussion, recent developments in physics have pushed the boundaries of this debate to new and still unexplored realms. For it is claimed that, in certain theories of quantum gravity, spacetime ‘disappears’: and this suggests that one may have sensible physical theories in which spacetime is completely absent. This makes the philosophical question whether such theories are intelligible, even more pressing. And if such theories are intelligible, the (...) question then is how they manage to do so. In this paper, we adapt the contextual theory of scientific understanding, developed by one of us, to fit the novel challenges posed by physical theories without spacetime. We construe understanding as a matter of skill rather than just knowledge. The appeal is thus to understanding, rather than explanation, because we will be concerned with the tools that scientists have at their disposal for understanding these theories. Our central thesis is that such physical theories can provide scientific understanding, and that such understanding does not require spacetimes of any sort. Our argument consists of four consecutive steps: We argue, from the general theory of scientific understanding, that although visualization is an oft-used tool for understanding, it is not a necessary condition for it; we criticise certain metaphysical preconceptions which can stand in the way of recognising how intelligibility without spacetime can be had; we catalogue tools for rendering theories without a spacetime intelligible; and we give examples of cases in which understanding is attained without a spacetime, and explain what kind of understanding these examples provide. (shrink)

The literature on the nature of understanding can be divided into two broad camps. Explanationists believe that it is knowledge of explanations that is key to understanding. In contrast, their manipulationist rivals maintain that understanding essentially involves an ability to manipulate certain representations. The aim of this paper is to provide a novel knowledge based account of understanding. More specifically, it proposes an account of maximal understanding of a given phenomenon in terms of fully comprehensive and maximally well-connected knowledge of (...) it and of degrees of understanding in terms of approximations to such knowledge. It is completed by a contextualist semantics for outright attributions of understanding according to which an attribution of understanding is true of one just in case one knows enough about it to perform some contextually determined task. It is argued that this account has an edge over both its explanationist and manipulationist competitors. (shrink)

The purpose of the present article is to explore the relationship between consciousness and understanding. To do so, I first briefly review recent work on the nature of both understanding and consciousness within philosophy and psychology. Building off of this work, I then defend the thesis that if one is conscious of a given content then one also understands that content. I argue that this conclusion can be drawn from the fact that understanding is associated with rational intention formation and (...) the fact that conscious access appears to involve the selective routing/broadcasting of representational content to neural systems that integrate information in order to select cognitive/behavioral intentions in conjunction with goals. Based on these premises I illustrate how a disruption to the rationality of a representation’s influence on intention formation would also remove any evidence that a person was conscious of the content of that representation... (shrink)

While the relation between visualization and scientific understanding has been a topic of long-standing discussion, recent developments in physics have pushed the boundaries of this debate to new and still unexplored realms. For it is claimed that, in certain theories of quantum gravity, spacetime ‘disappears’: and this suggests that one may have sensible physical theories in which spacetime is completely absent. This makes the philosophical question whether such theories are intelligible, even more pressing. And if such theories are intelligible, the (...) question then is how they manage to do so. In this paper, we adapt the contextual theory of scientific understanding, developed by one of us, to fit the novel challenges posed by physical theories without spacetime. We construe understanding as a matter of skill rather than just knowledge. The appeal is thus to understanding, rather than explanation, because we will be concerned with the tools that scientists have at their disposal for understanding these theories. Our central thesis is that such physical theories can provide scientific understanding, and that such understanding does not require spacetimes of any sort. Our argument consists of four consecutive steps: (a) We argue, from the general theory of scientific understanding, that although visualization is an oft-used tool for understanding, it is not a necessary condition for it; (b) we criticise certain metaphysical preconceptions which can stand in the way of recognising how intelligibility without spacetime can be had; (c) we catalogue tools for rendering theories without a spacetime intelligible; and (d) we give examples of cases in which understanding is attained without a spacetime, and explain what kind of understanding these examples provide. (shrink)

Name der Zeitschrift: Deutsche Zeitschrift für Philosophie Jahrgang: 67 Heft: 3 Seiten: 373-391.

It is often claimed—especially by scientific realists—that science provides understanding of the world only if its theories are (at least approximately) true descriptions of reality, in its observable as well as unobservable aspects. This paper critically examines this ‘realist thesis’ concerning understanding. A crucial problem for the realist thesis is that (as study of the history and practice of science reveals) understanding is frequently obtained via theories and models that appear to be highly unrealistic or even completely fictional. So we (...) face the dilemma of either giving up the realist thesis that understanding requires truth, or allowing for the possibility that in many if not all practical cases we do not have scientific understanding. I will argue that the first horn is preferable: the link between understanding and truth can be severed. This becomes a live option if we abandon the traditional view that scientific understanding is a special type of knowledge. While this view implies that understanding must be factive, I avoid this implication by identifying understanding with a skill rather than with knowledge. I will develop the idea that understanding phenomena consists in the ability to use a theory to generate predictions of the target system’s behavior. This implies that the crucial condition for understanding is not truth but intelligibility of the theory, where intelligibility is defined as the value that scientists attribute to the theoretical virtues that facilitate the construction of models of the phenomena. I will show, first, that my account accords with the way practicing scientists conceive of understanding, and second, that it allows for the use of idealized or fictional models and theories in achieving understanding. (shrink)

In this paper, I consider the relationship between coming to understand why something must be the case and coming to understand why it actually is the case in some particular instance. Peter Lipton uses the possibility of coming to understand a phenomenon via a necessity proof as an argument that there can be understanding with no explanation. Lipton’s argument has come under criticism, at least partially because one might think that understanding why something must be the case has a different (...) object from understanding the actual phenomenon. In this paper, I argue that that under certain circumstances it is fairly straightforward to come to understand an actual phenomenon on the basis of knowing why it had to be the case. Rather than relying on brute intuitions, my primary strategy will be to show that on least some modern accounts of understanding we can validate Lipton’s general point with respect to a variety of possible necessity relations. (shrink)

In this paper, I argue that explanations just ARE those sorts of things that, under the right circumstances and in the right sort of way, bring about understanding. This raises the question of why such a seemingly simple account of explanation, if correct, would not have been identified and agreed upon decades ago. The answer is that only recently has it been made possible to analyze explanation in terms of understanding without the risk of collapsing both to merely phenomenological states. (...) For the most part, theories of explanation were for 50 years held hostage to the historical accident that they far outstripped in sophistication corresponding accounts of understanding. (shrink)

In recent years, much attention has been given to the epistemic credentials of belief based on moral testimony. Some people think pure moral deference is wrong, others disagree. It comes as a surprise, however, that while the epistemic responsibilities of the receiver of moral testimony have been closely scrutinized, little to no discussion has focused on the epistemic duties of the speaker. This paper aims to supply this lack: it defends a function-first account of the normativity of moral assertion. According (...) to this view, in virtue of its function of reliably generating understanding in the audience, a moral assertion that p needs be knowledgeable and accompanied by a contextually appropriate explanation why p. (shrink)

I examine situations in which we say that different subjects have ‘different’, ‘competing’, or ‘conflicting understandings’ of a phenomenon. In order to make sense of such situations, we should turn our attention to an often neglected ambiguity in the word ‘understanding’. Whereas the notion of understanding that is typically discussed in philosophy is, to use Elgin’s terms, tethered to the facts, there is another notion of understanding that is not tethered in the same way. This latter notion is relevant because, (...) typically, talk of two subjects having ‘different’, ‘competing’, or ‘conflicting understandings’ of a phenomenon does not entail any commitment to the proposition that these subjects understand the phenomenon in the tethered sense of the word. This paper aims, first, to analyze the non-tethered notion of understanding, second, to clarify its relationship to the tethered notion, third, to explore what exactly goes on when ‘different’, ‘competing’, or ‘conflicting understandings’ clash and, fourth, to discuss the significance of such situations in our epistemic practices. In particular, I argue for a version of scientific pluralism according to which such situations are important because they help scientific communities achieve their fundamental epistemic goals—most importantly, the goal of understanding the world in the tethered sense. (shrink)

In this paper, I give an overview of different models of understanding attribution and advance a contextualist account of understanding attribution. Whereas other contextualist accounts make the degree in which the epistemic states of the relevant agents satisfy certain invariant conditions context-sensitive, the proposed account makes the conditions themselves context-sensitive.