对比因果推断与可解释AI中的反事实分析，揭示两者差异与融合可能。
From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI
- 统一定义反事实概念，涵盖因果推断与可解释AI的多重含义。
- 指出两领域在生成、评估与应用反事实时的核心差异。
- 为跨领域方法融合提供理论基础，适合关注AI可解释性的研究者。
反事实分析在因果推断（CI）和可解释人工智能（XAI）两个不同数据科学领域中均具有核心作用。尽管两领域对反事实的基本理解一致——即考察在不同条件下会发生什么，但在其使用方式与解读上存在关键差异。本文提出一个形式化定义，涵盖反事实在CI与XAI中的多面性。随后，我们系统比较了反事实在两领域中的生成、评估、使用与操作化过程，揭示其概念与实践层面的异同。通过对比，旨在发现两领域间交叉融合的潜在机会。
原文摘要 · Abstract (English)
Counterfactuals play a pivotal role in the two distinct data science fields of causal inference (CI) and explainable artificial intelligence (XAI). While the core idea behind counterfactuals remains the same in both fields--the examination of what would have happened under different circumstances--there are key differences in how they are used and interpreted. We introduce a formal definition that encompasses the multi-faceted concept of the counterfactual in CI and XAI. We then discuss how counterfactuals are used, evaluated, generated, and operationalized in CI vs. XAI, highlighting conceptual and practical differences. By comparing and contrasting the two, we hope to identify opportunities for cross-fertilization across CI and XAI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。