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

• URL: http://arxiv.org/abs/2505.13324v1
• Date: Mon, 19 May 2025 16:34:36 GMT
• Title: From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI
• Authors: Galit Shmueli, David Martens, Jaewon Yoo, Travis Greene,
• Abstract summary: Counterfactuals play a pivotal role in the two distinct data science fields of causal inference (CI) and explainable artificial intelligence (XAI)<n>We introduce a formal definition that encompasses the multi-faceted concept of the counterfactual in CI and XAI.<n>We discuss how counterfactuals are used, evaluated, generated, and operationalized in CI vs. XAI, highlighting conceptual and practical differences.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• When concept-based XAI is imprecise: Do people distinguish between generalisations and misrepresentations? [0.0]
  Concept-based explainable artificial intelligence (C-XAI) can help reveal the inner representations of AI models.<n>It may desirable for C-XAI concepts to show some variability.<n>It is unclear whether people recognise and appreciate such generalisations.
  arXiv  Detail & Related papers  (2025-06-22T08:07:02Z)
• The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms [3.3653074379567096]
  mechanistic interpretability (MI) has emerged as a distinct research area studying the features and implicit algorithms learned by foundation models such as large language models. We argue that current methods are ripe to facilitate a transition in deep learning interpretation echoing the "cognitive revolution" in 20th-century psychology. We propose a taxonomy mirroring key parallels in computational neuroscience to describe two broad categories of MI research.
  arXiv  Detail & Related papers  (2024-08-11T20:50:16Z)
• Take A Step Back: Rethinking the Two Stages in Visual Reasoning [57.16394309170051]
  This paper revisits visual reasoning with a two-stage perspective. It is more efficient to implement symbolization via separated encoders for different data domains while using a shared reasoner. The proposed two-stage framework achieves impressive generalization ability on various visual reasoning tasks.
  arXiv  Detail & Related papers  (2024-07-29T02:56:19Z)
• The role of causality in explainable artificial intelligence [1.049712834719005]
  Causality and eXplainable Artificial Intelligence (XAI) have developed as separate fields in computer science. We investigate the literature to try to understand how and to what extent causality and XAI are intertwined.
  arXiv  Detail & Related papers  (2023-09-18T16:05:07Z)
• How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding [56.222097640468306]
  We provide mechanistic understanding of how transformers learn "semantic structure" We show, through a combination of mathematical analysis and experiments on Wikipedia data, that the embedding layer and the self-attention layer encode the topical structure.
  arXiv  Detail & Related papers  (2023-03-07T21:42:17Z)
• A Means-End Account of Explainable Artificial Intelligence [0.0]
  XAI seeks opaque explanations for machine learning methods. Authors disagree on what should be explained (topic), whom something should be explained (stakeholder), how something should be explained (instrument), and why something should be explained (goal)
  arXiv  Detail & Related papers  (2022-08-09T09:57:42Z)
• The Who in XAI: How AI Background Shapes Perceptions of AI Explanations [61.49776160925216]
  We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. We find that (1) both groups showed unwarranted faith in numbers for different reasons and (2) each group found value in different explanations beyond their intended design.
  arXiv  Detail & Related papers  (2021-07-28T17:32:04Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)
• Explainability in Deep Reinforcement Learning [68.8204255655161]
  We review recent works in the direction to attain Explainable Reinforcement Learning (XRL) In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box.
  arXiv  Detail & Related papers  (2020-08-15T10:11:42Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.