# Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them

arXiv: https://arxiv.org/abs/2604.04518 · HTML: https://mlsanity.com/paper/2604.04518/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 136 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Deep learning generalizes because the parameter-function map is biased towards simple functions](https://mlsanity.com/paper/1805.08522/) (2018)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [Coping with Label Shift via Distributionally Robust Optimisation](https://mlsanity.com/paper/2010.12230/) (2020)
- [Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective](https://mlsanity.com/paper/2110.03095/) (2021)
- [Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation](https://mlsanity.com/paper/2412.05152/) (2024)
- [Increasing Robustness to Spurious Correlations using Forgettable Examples](https://mlsanity.com/paper/1911.03861/) (2019)
- [Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples](https://mlsanity.com/paper/2510.17524/) (2025)
- [Imbalanced Classification through the Lens of Spurious Correlations](https://mlsanity.com/paper/2510.27650/) (2025)
- [SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models](https://mlsanity.com/paper/2603.17048/) (2026)
- [Identifying Spurious Correlations using Counterfactual Alignment](https://mlsanity.com/paper/2312.02186/) (2023)

## Built on by (most cited first, 1 of 1)

- [Towards Fast and Disentangled Counterfactuals for Visual Foundation Models](https://mlsanity.com/paper/2610.00895/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and autonomous driving where model reliability is critical. However, the research landscape for ensuring this reliability is terminologically fractured across communities that pursue the same goal of ensuring models rely on causally relevant features rather than confounding signals. While frameworks such as distributionally robust optimization (DRO), invariant risk minimization (IRM), shortcut learning, simplicity bias, and the Clever Hans effect all address model failure due to spurious correlations, researchers typically only reference work within their own domains. This reproducibility study unifies these perspectives through a comparative analysis of correction methods under challenging constraints like limited data availability and severe subgroup imbalance. We evaluate recently proposed correction methods based on explainable artificial intelligence (XAI) techniques alongside popular non-XAI baselines using both synthetic and real-world datasets. Findings show that XAI-based methods generally outperform non-XAI approaches, with Counterfactual Knowledge Distillation (CFKD) proving most consistently effective at improving generalization. Our experiments also reveal that the practical application of many methods is hindered by a dependency on group labels, as manual annotation is often infeasible and automated tools like Spectral Relevance Analysis (SpRAy) struggle with complex features and severe imbalance. Furthermore, the scarcity of minority group samples in validation sets renders model selection and hyperparameter tuning unreliable, posing a significant obstacle to the deployment of robust and trustworthy models in safety-critical areas.