# Issues with post-hoc counterfactual explanations: a discussion

arXiv: https://arxiv.org/abs/1906.04774 · HTML: https://mlsanity.com/paper/1906.04774/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2019.

## Built on by (most cited first, 30 of 30)

- [Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees](https://mlsanity.com/paper/2305.11997/) (2023)
- [Evaluating Robustness of Counterfactual Explanations](https://mlsanity.com/paper/2103.02354/) (2021)
- [Consistent Counterfactuals for Deep Models](https://mlsanity.com/paper/2110.03109/) (2021)
- [Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks](https://mlsanity.com/paper/2410.02331/) (2024)
- [CARE: Coherent Actionable Recourse based on Sound Counterfactual Explanations](https://mlsanity.com/paper/2108.08197/) (2021)
- [Generating robust counterfactual explanations](https://mlsanity.com/paper/2304.12943/) (2023)
- [Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting](https://mlsanity.com/paper/2205.05515/) (2022)
- [Achieving Diversity in Counterfactual Explanations: a Review and Discussion](https://mlsanity.com/paper/2305.05840/) (2023)
- [Interpretable Machine Learning: Moving From Mythos to Diagnostics](https://mlsanity.com/paper/2103.06254/) (2021)
- [Stabilizing Estimates of Shapley Values with Control Variates](https://mlsanity.com/paper/2310.07672/) (2023)
- [The Risks of Recourse in Binary Classification](https://mlsanity.com/paper/2306.00497/) (2023)
- [Counterfactual Concept Bottleneck Models](https://mlsanity.com/paper/2402.01408/) (2024)
- [Understanding Prediction Discrepancies in Machine Learning Classifiers](https://mlsanity.com/paper/2104.05467/) (2021)
- [Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations](https://mlsanity.com/paper/2309.04676/) (2023)
- [Towards Conceptualization of "Fair Explanation": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators](https://mlsanity.com/paper/2310.15055/) (2023)
- [Why do explanations fail? A typology and discussion on failures in XAI](https://mlsanity.com/paper/2405.13474/) (2024)
- [Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical Reasoning](https://mlsanity.com/paper/2501.07021/) (2025)
- [Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures](https://mlsanity.com/paper/2503.07934/) (2025)
- [Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey](https://mlsanity.com/paper/2307.09615/) (2023)
- [Generally-Occurring Model Change for Robust Counterfactual Explanations](https://mlsanity.com/paper/2407.11426/) (2024)
- [Towards User Guided Actionable Recourse](https://mlsanity.com/paper/2309.02517/) (2023)
- [T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems](https://mlsanity.com/paper/2309.16146/) (2023)
- [Weak Robust Compatibility Between Learning Algorithms and Counterfactual Explanation Generation Algorithms](https://mlsanity.com/paper/2405.20664/) (2024)
- [In Defence of Post-hoc Explainability](https://mlsanity.com/paper/2412.17883/) (2024)
- [[Re] Improving Interpretation Faithfulness for Vision Transformers](https://mlsanity.com/paper/2509.14846/) (2025)
- [Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations](https://mlsanity.com/paper/2210.08902/) (2022)
- [Enhancing Counterfactual Image Generation Using Mahalanobis Distance with Distribution Preferences in Feature Space](https://mlsanity.com/paper/2405.20685/) (2024)
- [Structure-Aware Robust Counterfactual Explanations via Conditional Gaussian Network Classifiers](https://mlsanity.com/paper/2602.08021/) (2026)
- [We Need Explanation Cards to Connect Explanation Algorithms to the Real World](https://mlsanity.com/paper/2606.16786/) (2026)
- [Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models](https://mlsanity.com/paper/2606.29346/) (2026)

## Abstract (arXiv)

Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier. However, the assumptions they make about the data and the classifier make them unreliable in many contexts. In this paper, we discuss three desirable properties and approaches to quantify them: proximity, connectedness and stability. In addition, we illustrate that there is a risk for post-hoc counterfactual approaches to not satisfy these properties.