4 papers · 1 filter
Large Language Models as Nondeterministic Causal Models
Sander Beckers
Recent work by Chatzi et al. and Ravfogel et al. has developed, for the first time, a method for generating counterfactuals of probabilistic Large Language Models. Such counterfact…
Causal Counterfactuals Reconsidered
Sander Beckers
I develop a novel semantics for probabilities of counterfactuals that generalizes the standard Pearlian semantics: it applies to probabilistic causal models that cannot be extended…
Actual Causation and Nondeterministic Causal Models
Sander Beckers
In (Beckers, 2025) I introduced nondeterministic causal models as a generalization of Pearl's standard deterministic causal models. I here take advantage of the increased expressiv…
Nondeterministic Causal Models
Sander Beckers
I generalize acyclic deterministic structural causal models to the nondeterministic case and argue that this offers an improved semantics for counterfactuals. The standard, determi…