cs.AI · 2605.08688 Copy arXiv ID · May 9, 2026 Save Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations Authors: Leopoldo Bertossi
Organizations: Carleton University, Canada · IMFD, Chile · Emeritus Professor. Adjunct Professor Western University, Canada.
Abstract We establish, from the point of view of Explainable AI (XAI), connections between Consistency-Based Diagnosis (CBD), on one side, and Actual Causality and Causal Responsibility, on the other. CBD has received little attention from the XAI community. Connections between these two areas could have a fruitful impact on XAI and Explainable Data Management.
Explore similar work Sep 22, 2026 · Nicholas Tagliapietra, Florian Peter Busch, Moritz Willig +4
Aug 4, 2026 · Abhinav Thorat, Ravi Kumar Kolla, Vishak K Bhat +2 Causal Foundation Models Directed Acyclic Graph
Sep 3, 2026 · Rafal Urbaniak, Sam Witty, Daniel Waxman +7 Structural Causal Model Causal Reasoning
Sep 22, 2026 · cs.LG J/K move · Enter open · S save
Nicholas Tagliapietra, Florian Peter Busch, Moritz Willig, Matej Zečević +3
Explanations are central to causal reasoning, and cognitive science has long established that the human drive to explain is itself a mechanism for learning about causality. Despite this, learning from those abductive signals is largely ignored in artificial intelligence. While explainable AI (XAI) increasingly draws on causal models to generate explanations, the converse direction about what explanations can do for causality remains largely unexplored. To fill this gap, we propose xWhyL, a formal framework connecting causality and XAI by learning causal models from explanations. We develop a mathematical theory that translates explanations into a learning signal complementary to observational data, and demonstrate how it enables overcoming the limits of observational causal discovery. As explanations can be derived from incorrect beliefs and clash with data, a tension we call the Causal Tug-of-War, we prove conditions under which our framework rejects misspecified explanations rather than absorbing them. Our practical instantiation, Causal Interactive Learning (CIL), shows how expert explanations can efficiently support causal discovery and distinguish correct from incorrect explanations.