Sander Beckers

The ethical concerns regarding the successful development of an Artificial Intelligence have received a lot of attention lately. The idea is that even if we have good reason to believe that it is very unlikely, the mere possibility of an AI causing extreme human suffering is important enough to warrant serious consideration. Others look at this problem from the opposite perspective, namely that of the AI itself. Here the idea is that even if we have good reason to believe that it is very unlikely, the mere possibility of humanity causing extreme suffering to an AI is important enough to warrant serious consideration. This paper starts from the observation that both concerns rely on problematic philosophical assumptions. Rather than tackling these assumptions directly, it proceeds to present an argument that if one takes these assumptions seriously, then one has a moral obligation to advocate for a ban on the development of a conscious AI.

In this paper we present a new proposal for defining actual causation, i.e., the problem of deciding if one event caused another. We do so within the popular counterfactual tradition initiated by Lewis, which is characterised by attributing a fundamental role to counterfactual dependence. Unlike the currently prominent definitions, our approach proceeds from the ground up: we start from basic principles, and construct a definition of causation that satisfies them. We define the concepts of counterfactual dependence and production, and put forward principles such that dependence is an unnecessary but sufficient condition for causation, whereas production is an insufficient but necessary condition. The resulting definition of causation is a suitable compromise between dependence and production. Every principle is introduced by means of a paradigmatic example of causation. We illustrate some of the benefits of our approach with two examples that have spelled trouble for other accounts. We make all of this formally precise using structural equations, which we extend with a timing over all events.

The counterfactual tradition to defining actual causation has come a long way since Lewis started it off. However there are still important open problems that need to be solved. One of them is the (in)transitivity of causation. Endorsing transitivity was a major source of trouble for the approach taken by Lewis, which is why currently most approaches reject it. But transitivity has never lost its appeal, and there is a large literature devoted to understanding why this is so. Starting from a survey of this work, we will develop a formal analysis of transitivity and the problems it poses for causation. This analysis provides us with a sufficient condition for causation to be transitive, a sufficient condition for dependence to be necessary for causation, and several characterisations of the transitivity of dependence. Finally, we show how this analysis leads naturally to several conditions a definition of causation should satisfy, and use those to suggest a new definition of causation.

Andreas & Günther have recently proposed a difference-making definition of actual causation. In this paper I show that there exist conclusive counterexamples to their definition, by which I mean examples that are unacceptable to everyone, including AG. Concretely, I show that their definition allows c to cause e even when c is not a causal ancestor of e. I then proceed to identify their non-standard definition of causal models as the source of the problem, and argue that there is no viable strategy open to AG to fixing it. I conclude that their definition of causation is damaged beyond repair.

As more and more decisions that have a significant ethical dimension are being outsourced to AI systems, it is important to have a definition of moral responsibility that can be applied to AI systems. Moral responsibility for an outcome of an agent who performs some action is commonly taken to involve both a causal condition and an epistemic condition: the action should cause the outcome, and the agent should have been aware -- in some form or other -- of the possible moral consequences of their action. This paper presents a formal definition of both conditions within the framework of causal models. I compare my approach to the existing approaches of Braham and van Hees (BvH) and of Halpern and Kleiman-Weiner (HK). I then generalize my definition into a degree of responsibility.

As autonomous systems rapidly become ubiquitous, there is a growing need for a legal and regulatory framework that addresses when and how such a system harms someone. There have been several attempts within the philosophy literature to define harm, but none of them has proven capable of dealing with the many examples that have been presented, leading some to suggest that the notion of harm should be abandoned and “replaced by more well-behaved notions”. As harm is generally something that is caused, most of these definitions have involved causality at some level. Yet surprisingly, none of them makes use of causal models and the definitions of actual causality that they can express. In this paper, which is an expanded version of the conference paper Beckers et al. (Neurips, 2022), we formally define a qualitative notion of harm that uses causal models and is based on a well-known definition of actual causality. The key features of our definition are that it is based on contrastive causation and uses a default utility to which the utility of actual outcomes is compared. We show that our definition is able to handle the examples from the literature, and illustrate its importance for reasoning about situations involving autonomous systems.

Pearl opened the door to formally defining actual causation using causal models. His approach rests on two strategies: first, capturing the widespread intuition that X = x causes Y = y iff X = x is a Necessary Element of a Sufficient Set for Y = y, and second, showing that his definition gives intuitive answers on a wide set of problem cases. This inspired dozens of variations of his definition of actual causation, the most prominent of which are due to Halpern & Pearl. Yet all of them ignore Pearl’s first strategy, and the second strategy taken by itself is unable to deliver a consensus. This paper offers a way out by going back to the first strategy: it offers six formal definitions of causal sufficiency and two interpretations of necessity. Combining the two gives twelve new definitions of actual causation. Several interesting results about these definitions and their relation to the various Halpern & Pearl definitions are presented. Afterwards the second strategy is evaluated as well. In order to maximize neutrality, the paper relies mostly on the examples and intuitions of Halpern & Pearl. One definition comes out as being superior to all others, and is therefore suggested as a new definition of actual causation.

Although standard Machine Learning models are optimized for making predictions about observations, more and more they are used for making predictions about the results of actions. An important goal of Explainable Artificial Intelligence (XAI) is to compensate for this mismatch by offering explanations about the predictions of an ML-model which ensure that they are reliably action-guiding. As action-guiding explanations are causal explanations, the literature on this topic is starting to embrace insights from the literature on causal models. Here I take a step further down this path by formally defining the causal notions of sufficient explanations and counterfactual explanations. I show how these notions relate to (and improve upon) existing work, and motivate their adequacy by illustrating how different explanations are action-guiding under different circum- stances. Moreover, this work is the first to offer a formal definition of actual causation that is founded entirely in action-guiding explanations. Although the definitions are motivated by a focus on XAI, the analysis of causal explanation and actual causation applies in general. I also touch upon the significance of this work for fairness in AI by showing how actual causation can be used to improve the idea of path-specific counterfactual fairness.

Causal models have proven extremely useful in offering formal representations of causal relationships between a set of variables. Yet in many situations, there are non-causal relationships among variables. For example, we may want variables LDL, HDL, and TOT that represent the level of low-density lipoprotein cholesterol, the level of lipoprotein high-density lipoprotein cholesterol, and total cholesterol level, with the relation LDL+HDL=TOT. This cannot be done in standard causal models, because we can intervene simultaneously on all three variables. The goal of this paper is to extend standard causal models to allow for constraints on settings of variables. Although the extension is relatively straightforward, to make it useful we have to define a new intervention operation that disconnects a variable from a causal equation. We give examples showing the usefulness of this extension, and provide a sound and complete axiomatization for causal models with constraints.

Counterfactual reasoning -- envisioning hypothetical scenarios, or possible worlds, where some circumstances are different from what (f)actually occurred (counter-to-fact) -- is ubiquitous in human cognition. Conventionally, counterfactually-altered circumstances have been treated as "small miracles" that locally violate the laws of nature while sharing the same initial conditions. In Pearl's structural causal model (SCM) framework this is made mathematically rigorous via interventions that modify the causal laws while the values of exogenous variables are shared. In recent years, however, this purely interventionist account of counterfactuals has increasingly come under scrutiny from both philosophers and psychologists. Instead, they suggest a backtracking account of counterfactuals, according to which the causal laws remain unchanged in the counterfactual world; differences to the factual world are instead "backtracked" to altered initial conditions (exogenous variables). In the present work, we explore and formalise this alternative mode of counterfactual reasoning within the SCM framework. Despite ample evidence that humans backtrack, the present work constitutes, to the best of our knowledge, the first general account and algorithmisation of backtracking counterfactuals. We discuss our backtracking semantics in the context of related literature and draw connections to recent developments in explainable artificial intelligence (XAI).

The ethical concerns regarding the successful development of an Artificial Intelligence have received a lot of attention lately. The idea is that even if we have good reason to believe that it is very unlikely, the mere possibility of an AI causing extreme human suffering is important enough to warrant serious consideration. Others look at this problem from the opposite perspective, namely that of the AI itself. Here the idea is that even if we have good reason to believe that it is very unlikely, the mere possibility of humanity causing extreme suffering to an AI is important enough to warrant serious consideration. This paper starts from the observation that both concerns rely on problematic philosophical assumptions. Rather than tackling these assumptions directly, it proceeds to present an argument that if one takes these assumptions seriously, then one has a moral obligation to advocate for a ban on the development of a conscious AI.

As autonomous systems rapidly become ubiquitous, there is a growing need for a legal and regulatory framework to address when and how such a system harms someone. There have been several attempts within the philosophy literature to define harm, but none of them has proven capable of dealing with with the many examples that have been presented, leading some to suggest that the notion of harm should be abandoned and "replaced by more well-behaved notions". As harm is generally something that is caused, most of these definitions have involved causality at some level. Yet surprisingly, none of them makes use of causal models and the definitions of actual causality that they can express. In this paper we formally define a qualitative notion of harm that uses causal models and is based on a well-known definition of actual causality (Halpern, 2016). The key novelty of our definition is that it is based on contrastive causation and uses a default utility to which the utility of actual outcomes is compared. We show that our definition is able to handle the examples from the literature, and illustrate its importance for reasoning about situations involving autonomous systems.

Beckers & Vennekens recently proposed a definition of actual causation that is based on certain plausible principles, thereby allowing the debate on causation to shift away from its heavy focus on examples towards a more systematic analysis. This paper contributes to that analysis in two ways. First, I show that their definition is in fact a formalization of Wright’s famous NESS definition of causation combined with a counterfactual difference-making condition. This means that their definition integrates two highly influential approaches to causation that are claimed to stand in opposition to each other. Second, I modify their definition to offer a substantial improvement: I weaken their difference-making condition in such a way that it avoids their problematic analysis of cases of preemption. The resulting Counterfactual NESS definition of causation forms a natural compromise between counterfactual approaches and the NESS approach.

Scientific models describe natural phenomena at different levels of abstraction. Abstract descriptions can provide the basis for interventions on the system and explanation of observed phenomena at a level of granularity that is coarser than the most fundamental account of the system. Beckers and Halpern (2019), building on work of Rubenstein et al. (2017), developed an account of abstraction for causal models that is exact. Here we extend this account to the more realistic case where an abstract causal model offers only an approximation of the underlying system. We show how the resulting account handles the discrepancy that can arise between low- and high-level causal models of the same system, and in the process provide an account of how one causal model approximates another, a topic of independent interest. Finally, we extend the account of approximate abstractions to probabilistic causal models, indicating how and where uncertainty can enter into an approximate abstraction.

The aim of this paper is to offer the first systematic exploration and definition of equivalent causal models in the context where both models are not made up of the same variables. The idea is that two models are equivalent when they agree on all "essential" causal information that can be expressed using their common variables. I do so by focussing on the two main features of causal models, namely their structural relations and their functional relations. In particular, I define several relations of causal ancestry and several relations of causal sufficiency, and require that the most general of these relations are preserved across equivalent models.

We consider a sequence of successively more restrictive definitions of abstraction for causal models, starting with a notion introduced by Rubenstein et al. (2017) called exact transformation that applies to probabilistic causal models, moving to a notion of uniform transformation that applies to deterministic causal models and does not allow differences to be hidden by the "right" choice of distribution, and then to abstraction, where the interventions of interest are determined by the map from low-level states to high-level states, and strong abstraction, which takes more seriously all potential interventions in a model, not just the allowed interventions. We show that procedures for combining micro-variables into macro-variables are instances of our notion of strong abstraction, as are all the examples considered by Rubenstein et al.