Publikation
xWhyL: Causal Interactive Learning
Nicholas Tagliapietra; Florian Peter Busch; Moritz Willig; Matej Zecevic; Lavdim Halilaj; Juergen Luettin; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2609.26037, Pages 1-26, arXiv, 2026.
Zusammenfassung
Explanations are central to causal reasoning, and cognitive science has long es-
tablished 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 expla-
nations into a learning signal complementary to observational data, and demonstrate
how it enables overcoming the limits of observational causal discovery. As expla-
nations 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 Learning1 (CIL), shows how expert explanations can efficiently
support causal discovery and distinguish correct from incorrect explanations.