Causal Explanations Over Time: Articulated Reasoning for Interactive Environments

2025/06/04 by Sebastian Rödling, Matej Zečević, Rödling, Sebastian +5
Computer Science · #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Logic, Reasoning, and Knowledge

paper · pdf · doi:10.48550/arxiv.2506.03915

openalex publication_date 2025/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Structural Causal Explanations (SCEs) can be used to automatically generate explanations in natural language to questions about given data that are grounded in a (possibly learned) causal model. Unfortunately they work for small data only. In turn they are not attractive to offer reasons for events, e.g., tracking causal changes over multiple time steps, or a behavioral component that involves feedback loops through actions of an agent. To this end, we generalize SCEs to a (recursive) formulation of explanation trees to capture the temporal interactions between reasons. We show the benefits of this more general SCE algorithm on synthetic time-series data and a 2D grid game, and further compare it to the base SCE and other existing methods for causal explanations.

Citations

• CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
• Causal Explanations of Structural Causal Models
• Explaining Black-Box Algorithms Using Probabilistic Contrastive\n Counterfactuals
• Zero-Shot Text-to-Image Generation
• Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
• Differentiable Causal Discovery from Interventional Data
• Language Models are Few-Shot Learners
• Feature relevance quantification in explainable AI: A causal problem
• CXPlain: Causal Explanations for Model Interpretation under Uncertainty
• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
• Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
• Quantifying Generalization in Reinforcement Learning
• DAGs with NO TEARS: Continuous Optimization for Structure Learning
• A Unified Approach to Interpreting Model Predictions
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• Discovering Graphical Granger Causality Using the Truncating Lasso\n Penalty

Related

• Causal Explanations of Structural Causal Models
• Explainable agency: human preferences for simple or complex explanations
• e-CARE: a New Dataset for Exploring Explainable Causal Reasoning
• Causes and Explanations: A Structural-Model Approach. Part II: Explanations
• Temporal Causal Reasoning with (Non-Recursive) Structural Equation Models