Uncertainty in Causality: A New Frontier

Understanding uncertainty in causality is vital in various domains, including core NLP tasks like event causality extraction, commonsense reasoning, and counterfactual text generation. However, existing literature lacks a comprehensive examination of this area. This survey aims to fill this gap by thoroughly reviewing the uncertainty in causality. We first introduce a novel trichotomy, categorizing causal uncertainty into aleatoric (inherent randomness in causal data), epistemic (causal model limitations), and ontological (existence of causal links) uncertainty. We then survey methods for quantifying uncertainty in causal analysis and highlight the complementary relationship between causal uncertainty and causal strength. Furthermore, we examine the challenges that large language models (LLMs) face in handling causal uncertainty, such as hallucinations and inconsistencies, and propose key traits for an optimal causal LLM. Our paper reviews current approaches and outlines future research directions, aiming to serve as a practical guide for researchers and practitioners in this emerging field. Uncertainty in Causality Taxonomy of Causal Uncertainty ( § 2) Aleatoric Uncertainty ( § 2.1) Definition: Uncertainty derived from inherent randomness or unpredictability in causality. Subcategories: (i) Random variability; (ii) Measurement noise. Literature: (Nalatore et al., 2007), (Knaeble et al., 2023), (Wang et al., 2023b). Epistemic Uncertainty ( § 2.2) Definition: uncertainty stemming from incomplete knowledge about causal relationships. Subcategories: (i) Structural design uncertainty; (ii) Parameter uncertainty. Literature: (Jesson et al., 2020), (Zhang et al., 2023b). Ontological Uncertainty ( § 2.3) Definition: uncertainty related to the existence of the causal link between the cause and the effect. Subcategories: (i) Existential uncertainty; (ii) Probabilistic uncertainty; (iii) Contextual uncertainty.