Cognitive Science, Volume 46, Issue 5, May 2022.

Explainable artificial intelligence (XAI) aims to help people understand black box algorithms, particularly of their outputs. But what are these explanations and when is one explanation better than another? The manipulationist definition of explanation from the philosophy of science offers good answers to these questions, holding that an explanation consists of a generalization that shows what happens in counterfactual cases. Furthermore, when it comes to explanatory depth this account holds that a generalization that has more abstract variables, is broader in (...) scope and/or more accurate is better. By applying these definitions and contrasting them with alternative definitions in the XAI literature I hope to help clarify what a good explanation is for AI. (shrink)

In domains like stock brokerage, clinical psychiatry, and long‐term political forecasting, experts generally fail to outperform novices. Empirical researchers agree on why this is: experts must receive direct or environmental learning feedback during training to develop reliable expertise, and these domains are deficient in this type of feedback. A growing number of philosophers resource this consensus view to argue that, given the absence of direct or environmental philosophical feedback, we should not give the philosophical intuitions or theories of expert philosophers (...) greater credence than those of novice philosophers. This article has three objectives. The first is to explore several overlooked issues concerning the strategy of generalizing from empirical studies of non‐philosophical expertise to the epistemic status of philosophical expertise. The second is to explain why empirical research into a causal relationship between direct learning feedback and enhanced expert performance does not provide good grounds for abandoning a default optimism about the epistemic superiority of expert philosophical theories. The third is to sketch a positive characterization of learning feedback that addresses developmental concerns made salient by the empirical literature on expert performance for specifically theory‐driven or “armchair” domains like philosophy. (shrink)

Changes in synaptic strength are described as a unifying hypothesis for memory formation and storage, leading philosophers to consider the ‘synaptic efficacy hypothesis’ as a paradigmatic explanation in neuroscience. Craver’s mosaic view has been influential in understanding synaptic efficacy by presenting long-term potentiation as a multi-level mechanism nested within a multi-level structure. This paper argues that the mosaic view fails to fully capture the explanatory power of the synaptic efficacy hypothesis due to assumptions about multi-level mechanisms. I present an alternative (...) approach that emphasizes the explanatory function of unification, accounting for the widespread consensus in neuroscience regarding synaptic efficacy by highlighting the stability of synaptic causal variables across different multi-level mechanisms. (shrink)

Are causal explanations (e.g., “she switched careers because of the COVID pandemic”) treated differently from the corresponding claims that one factor caused another (e.g., “the COVID pandemic caused her to switch careers”)? We examined whether explanatory and causal claims diverge in their responsiveness to two different types of information: covariation strength and mechanism information. We report five experiments with 1,730 participants total, showing that compared to judgments of causal strength, explanatory judgments tend to bemoresensitive to mechanism andlesssensitive to covariation – (...) even though explanatory judgments respond to both types of information. We also report exploratory comparisons to judgments of understanding, and discuss implications of our findings for theories of explanation, understanding, and causal attribution. These findings shed light on the potentially unique role of explanation in cognition. (shrink)

We report three experiments investigating whether people’s judgments about causal relationships are sensitive to the robustness or stability of such relationships across a range of background circumstances. In Experiment 1, we demonstrate that people are more willing to endorse causal and explanatory claims based on stable (as opposed to unstable) relationships, even when the overall causal strength of the relationship is held constant. In Experiment 2, we show that this effect is not driven by a causal generalization’s actual scope of (...) application. In Experiment 3, we offer evidence that stable causal relationships may be seen as better guides to action. Collectively, these experiments document a previously underappreciated factor that shapes people’s causal reasoning: the stability of the causal relationship. (shrink)

Recent philosophical work on causation has focused on distinctions across types of causal relationships. This paper argues for another distinction that has yet to receive attention in this work. This distinction has to do with whether causal relationships have “material continuity,” which refers to the reliable movement of material from cause to effect. This paper provides an analysis of material continuity and argues that causal relationships with this feature are associated with a unique explanatory perspective, are studied with distinct causal (...) investigative methods, and provide different types of causal control over their effects. (shrink)