# Debugging Tests for Model Explanations

arXiv: https://arxiv.org/abs/2011.05429 · HTML: https://mlsanity.com/paper/2011.05429/

## Key facts

- Cited by 147 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 30 of 147)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [HIVE: Evaluating the Human Interpretability of Visual Explanations](https://mlsanity.com/paper/2112.03184/) (2021)
- [Tracr: Compiled Transformers as a Laboratory for Interpretability](https://mlsanity.com/paper/2301.05062/) (2023)
- [A Consistent and Efficient Evaluation Strategy for Attribution Methods](https://mlsanity.com/paper/2202.00449/) (2022)
- [Do Feature Attribution Methods Correctly Attribute Features?](https://mlsanity.com/paper/2104.14403/) (2021)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [Leveraging Sparse Linear Layers for Debuggable Deep Networks](https://mlsanity.com/paper/2105.04857/) (2021)
- [Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models](https://mlsanity.com/paper/2502.12892/) (2025)
- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- ["Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification](https://mlsanity.com/paper/2111.07367/) (2021)
- [Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry](https://mlsanity.com/paper/2503.01822/) (2025)
- [Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation](https://mlsanity.com/paper/2212.04629/) (2022)
- [Explanation-Based Human Debugging of NLP Models: A Survey](https://mlsanity.com/paper/2104.15135/) (2021)
- [Leveraging Explanations in Interactive Machine Learning: An Overview](https://mlsanity.com/paper/2207.14526/) (2022)
- [Do Input Gradients Highlight Discriminative Features?](https://mlsanity.com/paper/2102.12781/) (2021)
- [FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods](https://mlsanity.com/paper/2308.06248/) (2023)
- [Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability](https://mlsanity.com/paper/2207.09615/) (2022)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [Visual correspondence-based explanations improve AI robustness and human-AI team accuracy](https://mlsanity.com/paper/2208.00780/) (2022)
- [Finding and Fixing Spurious Patterns with Explanations](https://mlsanity.com/paper/2106.02112/) (2021)
- [Evaluating Saliency Methods for Neural Language Models](https://mlsanity.com/paper/2104.05824/) (2021)

## Abstract (arXiv)

We investigate whether post-hoc model explanations are effective for diagnosing model errors--model debugging. In response to the challenge of explaining a model's prediction, a vast array of explanation methods have been proposed. Despite increasing use, it is unclear if they are effective. To start, we categorize textitbugs, based on their source, into:~textitdata, model, and test-time contamination bugs. For several explanation methods, we assess their ability to: detect spurious correlation artifacts (data contamination), diagnose mislabeled training examples (data contamination), differentiate between a (partially) re-initialized model and a trained one (model contamination), and detect out-of-distribution inputs (test-time contamination). We find that the methods tested are able to diagnose a spurious background bug, but not conclusively identify mislabeled training examples. In addition, a class of methods, that modify the back-propagation algorithm are invariant to the higher layer parameters of a deep network; hence, ineffective for diagnosing model contamination. We complement our analysis with a human subject study, and find that subjects fail to identify defective models using attributions, but instead rely, primarily, on model predictions. Taken together, our results provide guidance for practitioners and researchers turning to explanations as tools for model debugging.