xWhyL 框架：从解释中学习因果模型
xWhyL: Causal Interactive Learning
一篇反向思路的研究：不是用因果模型生成解释，而是把人类解释当学习信号来发现因果结构，还证明了何时该拒绝错误解释。
论文提出 xWhyL，一个连接因果推理与可解释 AI（XAI）的形式化框架，核心思路是把专家解释转化为与观测数据互补的学习信号。作者开发了相应的数学理论，说明解释如何帮助突破观测因果发现的局限。针对解释可能来自错误信念、与数据冲突的 Causal Tug-of-War 问题，论文证明了框架能拒绝错误解释而非吸收它们的条件。实践实现 Causal Interactive Learning（CIL）展示了专家解释如何高效支持因果发现，并区分正确与错误解释。
xWhyL: Causal Interactive Learning
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.
