xWhyL: Causal Interactive Learning

2026-09-22

AI Summary

本文提出xWhyL框架，通过从解释中学习因果模型来填补因果推理与可解释AI之间的空白，解决观察数据局限性问题。

Abstract

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.

Problem

• causal reasoning
• explainable AI
• causal discovery

Innovation

• causal models
• XAI
• explanations as learning signals
• observational data limitations
• Causal Tug-of-War