From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shmueli, Galit, Martens, David, Yoo, Jaewon, Greene, Travis
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918025298444288
author Shmueli, Galit
Martens, David
Yoo, Jaewon
Greene, Travis
author_facet Shmueli, Galit
Martens, David
Yoo, Jaewon
Greene, Travis
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13324
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI
Shmueli, Galit
Martens, David
Yoo, Jaewon
Greene, Travis
Machine Learning
Artificial Intelligence
Econometrics
Methodology
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.
title From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI
topic Machine Learning
Artificial Intelligence
Econometrics
Methodology
url https://arxiv.org/abs/2505.13324