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)

While discussions of the imagination have been limited in philosophy of science, this is beginning to change. In recent years, a vast literature on imagination in science has emerged. This paper surveys the current field, including the changing attitudes towards the scientific imagination, the fiction view of models, how the imagination can lead to knowledge and understanding, and the value of different types of imagination. It ends with a discussion of the gaps in the current literature, indicating avenues for future (...) research. (shrink)

Until recently, leading work on the philosophy of thought experiments mistakenly credited Mach with coining the term. While Ørsted’s prior use has become more widely acknowledged, there remains a c...

The Turing test has been studied and run as a controlled experiment and found to be underspecified and poorly designed. On the other hand, it has been defended and still attracts interest as a test for true artificial intelligence (AI). Scientists and philosophers regret the test’s current status, acknowledging that the situation is at odds with the intellectual standards of Turing’s works. This article refers to this as the Turing Test Dilemma, following the observation that the test has been under (...) discussion for over seventy years and still is widely seen as either too bad or too good to be a valuable experiment for AI. An argument that solves the dilemma is presented, which relies on reconstructing the Turing test as a thought experiment in the modern scientific tradition. It is argued that Turing’s exposition of the imitation game satisfies Mach’s characterization of the basic method of thought experiments and that Turing’s uses of his test satisfy Popper’s conception of the critical and heuristic uses of thought experiments and Kuhn’s association of thought experiments to conceptual change. It is emphasized how Turing methodically varied the imitation game design to address specific challenges posed to him by other thinkers and how his test illustrates a property of the phenomenon of intelligence and suggests a hypothesis on machine learning. This reconstruction of the Turing test provides a rapprochement to the conflicting views on its value in the literature. (shrink)

Ratio Juris, Volume 34, Issue 4, Page 356-385, December 2021.

Ronald Dworkin is one of the most frequently cited legal philosophers. His work, notably his attack on H. L. A. Hart's positivist theory of law, has received considerable attention, earning him praise as well as trenchant criticism. Instead of discussing the analytical validity of Dworkin's claims, though, we propose an alternative reading of his jurisprudential writings that emphasises their rhetorical nature. After delineating the rhetorical context of his work, we provide several illustrations of his use of rhetorical strategies and, with (...) the help of sentiment‐analysis techniques, emotional language. While resorting to classical rhetorical tactics, Dworkin's rhetoric, we argue, appealed to the emotional power of rights talk at a time when the notion of rights enjoyed greater resonance with his audience. (shrink)

In order to carry out “a great and important piece of work, and that in a complete and lasting way”, Kant claims that one must join one’s “effort with that of the author”. The reading of a work, therefore, must try to embrace “the articulation or structure of the system, which yet matters most when it comes to judging its unity and soundness”. This structure and articulation, however, may not be so easily accessible; it may, rather, be latent under “bright (...) colours [that] paint over and make unrecognizable” the argument’s essence, often confusing the reader, who “cannot quickly enough attain a survey of the whole”. Now, it would be expected, then, that Kant, condemning such “ornaments”, would not employ those resources I n his writings. However, it is curious that not infrequently he makes use of such “bright colours”. The present paper aims at pointing out some passages of Kant's theoretical and practical philosophy in which it is possible to identify such “colouring”. (shrink)

This paper presents an attempt to describe Józef Tischner’s philosophy of drama from the point of view of Larry Laudan’s philosophy of science. That is achieved with the help of the concept of Philosophical Research Traditions developed in the paper. A~certain conceptual problem of Tischner’s philosophy, and some future research topics are also presented.