# The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations

arXiv: https://arxiv.org/abs/1907.09294 · HTML: https://mlsanity.com/paper/1907.09294/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2019.

## Built on by (most cited first, 30 of 97)

- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango](https://mlsanity.com/paper/2209.07686/) (2022)
- [CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms](https://mlsanity.com/paper/2108.00783/) (2021)
- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications](https://mlsanity.com/paper/2103.04244/) (2021)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Learning Bottleneck Concepts in Image Classification](https://mlsanity.com/paper/2304.10131/) (2023)
- [Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties](https://mlsanity.com/paper/2103.08951/) (2021)
- [This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations](https://mlsanity.com/paper/2310.18589/) (2023)
- [Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies](https://mlsanity.com/paper/2107.09951/) (2021)
- [On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations](https://mlsanity.com/paper/2201.09051/) (2022)
- [Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?](https://mlsanity.com/paper/2401.12902/) (2024)
- [Interpretable Geometric Deep Learning via Learnable Randomness Injection](https://mlsanity.com/paper/2210.16966/) (2022)
- [Scalable Interpretability via Polynomials](https://mlsanity.com/paper/2205.14108/) (2022)
- [Interpretable Image Classification with Adaptive Prototype-based Vision Transformers](https://mlsanity.com/paper/2410.20722/) (2024)
- [Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations](https://mlsanity.com/paper/2106.13876/) (2021)
- [Counterfactual Shapley Additive Explanations](https://mlsanity.com/paper/2110.14270/) (2021)
- [Equivariant and Invariant Grounding for Video Question Answering](https://mlsanity.com/paper/2207.12783/) (2022)
- [Characterizing the risk of fairwashing](https://mlsanity.com/paper/2106.07504/) (2021)
- [Attribution-based Explanations that Provide Recourse Cannot be Robust](https://mlsanity.com/paper/2205.15834/) (2022)
- [The privacy issue of counterfactual explanations: explanation linkage attacks](https://mlsanity.com/paper/2210.12051/) (2022)
- [Improvement-Focused Causal Recourse (ICR)](https://mlsanity.com/paper/2210.15709/) (2022)
- [VCNet: A self-explaining model for realistic counterfactual generation](https://mlsanity.com/paper/2212.10847/) (2022)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [A Few Good Counterfactuals: Generating Interpretable, Plausible and Diverse Counterfactual Explanations](https://mlsanity.com/paper/2101.09056/) (2021)
- [MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment](https://mlsanity.com/paper/2401.08527/) (2024)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [CARE: Coherent Actionable Recourse based on Sound Counterfactual Explanations](https://mlsanity.com/paper/2108.08197/) (2021)
- [Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions](https://mlsanity.com/paper/2107.09734/) (2021)

## Abstract (arXiv)

Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the risk of having explanations that are a result of some artifacts learned by the model instead of actual knowledge from the data. This paper focuses on the case of counterfactual explanations and asks whether the generated instances can be justified, i.e. continuously connected to some ground-truth data. We evaluate the risk of generating unjustified counterfactual examples by investigating the local neighborhoods of instances whose predictions are to be explained and show that this risk is quite high for several datasets. Furthermore, we show that most state of the art approaches do not differentiate justified from unjustified counterfactual examples, leading to less useful explanations.