mlsanityData to 14 Oct 2026

For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI

arXiv 2306.07637 ↗First posted 13 Jun 2023cs.AI cs.HCcited by 4

Not on the map. Why?

Abstract (arXiv)

Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI), highlighting changes to input data necessary for altering a model's output. A CFE can either describe a scenario that is better than the factual state (upward CFE), or a scenario that is worse than the factual state (downward CFE). However, potential benefits and drawbacks of the directionality of CFEs for user behavior in xAI remain unclear. The current user study (N=161) compares the impact of CFE directionality on behavior and experience of participants tasked to extract new knowledge from an automated system based on model predictions and CFEs. Results suggest that upward CFEs provide a significant performance advantage over other forms of counterfactual feedback. Moreover, the study highlights potential benefits of mixed CFEs improving user performance compared to downward CFEs or no explanations. In line with the performance results, users' explicit knowledge of the system is statistically higher after receiving upward CFEs compared to downward comparisons. These findings imply that the alignment between explanation and task at hand, the so-called regulatory fit, may play a crucial role in determining the effectiveness of model explanations, informing future research directions in xAI. To ensure reproducible research, the entire code, underlying models and user data of this study is openly available: https://github.com/ukuhl/DirectionalAlienZoo

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 69 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

23 of 69 references.

References · 23

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  3. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  4. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  5. 2018Actionable Recourse in Linear Classificationcited by 328
  6. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  7. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  8. 2022The Shapley Value in Machine Learningcited by 98
  9. 2020Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)cited by 79
  10. 2019Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanationscited by 64
  11. 2018Interpretable Credit Application Predictions With Counterfactual Explanationscited by 43
  12. 2021Evaluating Robustness of Counterfactual Explanationscited by 41
11 more
  1. 2019CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence modelscited by 34
  2. 2019On the computation of counterfactual explanations -- A surveycited by 33
  3. 2021Conditional Generative Models for Counterfactual Explanationscited by 28
  4. 2021Learning Accurate and Interpretable Decision Rule Sets from Neural Networkscited by 25
  5. 2021Amortized Generation of Sequential Algorithmic Recourses for Black-box Modelscited by 24
  6. 2022Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAIcited by 16
  7. 2021Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learningcited by 15
  8. 2021Model-Based Counterfactual Synthesizer for Interpretationcited by 14
  9. 2022Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Settingcited by 11
  10. 2022Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learningcited by 9
  11. 2021Understanding Consumer Preferences for Explanations Generated by XAI Algorithmscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessmentscited by 8
  2. 2025When Bias Backfires: The Modulatory Role of Counterfactual Explanations on the Adoption of Algorithmic Bias in XAI-Supported Human Decision-Makingcited by 2
  3. 2026Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustmentscited by 1
  4. 2026Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanationscited by 0