Recent work has developed, for the first time, a method for generating counterfactuals of probabilistic Large Language Models. Such counterfactuals tell us what would – or might – have been the output of an LLM if some factual prompt x had been x* instead. The ability to generate such counterfactuals is an important necessary step towards explaining, evaluating, and eventually improving, the behavior of LLMs. I argue, however, that the existing method rests on an ambiguous interpretation of LLMs: it does not interpret LLMs literally, for the method involves the assumption that one can change the implementation of an LLM’s sampling process without changing the LLM itself, nor does it interpret LLMs as intended, for the method involves explicitly representing a nondeterministic LLM as a deterministic causal model. I here present a much simpler method for generating counterfactuals that is based on an LLM’s intended interpretation by representing it as a nondeterministic causal model instead. The advantage of this simpler method is that it is directly applicable to any black-box LLM without modification, as it is agnostic to any implementation details. The advantage of the existing method, on the other hand, is that it directly implements the generation of a specific type of counterfactuals that is useful for certain purposes, but not for others. I clarify how both methods relate by offering a theoretical foundation for reasoning about counterfactuals in LLMs based on their intended semantics, thereby laying the groundwork for novel application-specific methods for generating counterfactuals.

In earlier work we defined a qualitative notion of harm: either harm is caused, or it is not. For practical applications, we often need to quantify harm; for example, we may want to choose the least harmful of a set of possible interventions. We first present a quantitative definition of harm in a deterministic context involving a single individual, then we consider the issues involved in dealing with uncertainty regarding the context and going from a notion of harm for a single individual to a notion of "societal harm", which involves aggregating the harm to individuals. We show that the "obvious" way of doing this (just taking the expected harm for an individual and then summing the expected harm over all individuals) can lead to counterintuitive or inappropriate answers, and discuss alternatives, drawing on work from the decision-theory literature.

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 toaddress 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.

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.

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.