# Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation

arXiv: https://arxiv.org/abs/2412.05152 · HTML: https://mlsanity.com/paper/2412.05152/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 225 references that are in the map.
- First posted on arXiv 6 Dec 2024.

## Builds on (most cited first, 30 of 45)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [The pitfalls of next-token prediction](https://mlsanity.com/paper/2403.06963/) (2024)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Understanding the Failure Modes of Out-of-Distribution Generalization](https://mlsanity.com/paper/2010.15775/) (2020)
- [Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation](https://mlsanity.com/paper/2204.02070/) (2022)
- [Extending the WILDS Benchmark for Unsupervised Adaptation](https://mlsanity.com/paper/2112.05090/) (2021)
- [MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts](https://mlsanity.com/paper/2202.06523/) (2022)
- [Causal Representation Learning from Multiple Distributions: A General Setting](https://mlsanity.com/paper/2402.05052/) (2024)
- [Concept-level Debugging of Part-Prototype Networks](https://mlsanity.com/paper/2205.15769/) (2022)
- [Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases](https://mlsanity.com/paper/2303.05470/) (2023)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Finding and Fixing Spurious Patterns with Explanations](https://mlsanity.com/paper/2106.02112/) (2021)
- [Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA](https://mlsanity.com/paper/2210.04692/) (2022)
- [Learning to Intervene on Concept Bottlenecks](https://mlsanity.com/paper/2308.13453/) (2023)
- [Understanding Rare Spurious Correlations in Neural Networks](https://mlsanity.com/paper/2202.05189/) (2022)
- [Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground](https://mlsanity.com/paper/2211.12883/) (2022)

## Built on by (most cited first, 25 of 25)

- [Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation](https://mlsanity.com/paper/2506.21876/) (2025)
- [Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens](https://mlsanity.com/paper/2502.11245/) (2025)
- [Chunky Post-Training: Data Driven Failures of Generalization](https://mlsanity.com/paper/2602.05910/) (2026)
- [Synthesizing Visual Concepts as Vision-Language Programs](https://mlsanity.com/paper/2511.18964/) (2025)
- [QuAnTS: Question Answering on Time Series](https://mlsanity.com/paper/2511.05124/) (2025)
- [IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions](https://mlsanity.com/paper/2602.21226/) (2026)
- [Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More](https://mlsanity.com/paper/2503.10542/) (2025)
- [VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation](https://mlsanity.com/paper/2508.18933/) (2025)
- [Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion Recognition](https://mlsanity.com/paper/2506.19079/) (2025)
- [Bias in the Shadows: Explore Shortcuts in Encrypted Network Traffic Classification](https://mlsanity.com/paper/2601.10180/) (2026)
- [Factored Causal Representation Learning for Robust Reward Modeling in RLHF](https://mlsanity.com/paper/2601.21350/) (2026)
- [Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them](https://mlsanity.com/paper/2604.04518/) (2026)
- [Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers](https://mlsanity.com/paper/2604.14477/) (2026)
- [Table2Image: Lightweight Tabular Learning with Generated Proxy Representations and Reliability Diagnostics](https://mlsanity.com/paper/2412.06265/) (2024)
- [Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings](https://mlsanity.com/paper/2507.07532/) (2025)
- [Diagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)](https://mlsanity.com/paper/2510.00475/) (2025)
- [Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study](https://mlsanity.com/paper/2602.18502/) (2026)
- [The Infinite-Dimensional Nature of Spectroscopy and Why Models Succeed, Fail, and Mislead](https://mlsanity.com/paper/2604.04717/) (2026)
- [A Toolkit for Detecting Spurious Correlations in Speech Datasets](https://mlsanity.com/paper/2604.26676/) (2026)
- [Receipt Replay OOD: A Small Benchmark for Screen Replay Detection Under Domain Shift](https://mlsanity.com/paper/2605.26855/) (2026)
- [Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility](https://mlsanity.com/paper/2606.15251/) (2026)
- [COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives](https://mlsanity.com/paper/2606.28194/) (2026)
- [Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations](https://mlsanity.com/paper/2609.34030/) (2026)
- [Event Cameras for Melt-Pool Monitoring in Additive Manufacturing: A Benchmark and a Cross-Machine Transfer Analysis](https://mlsanity.com/paper/2610.06973/) (2026)
- [AnyBottle: A Recipe to Only Keep the Concepts You Really Need](https://mlsanity.com/paper/2610.08552/) (2026)

## Abstract (arXiv)

Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in this area, however, remains fragmented across various terminologies, hindering the progress of the field as a whole. Consequently, we introduce a unifying taxonomy of shortcut learning by providing a formal definition of shortcuts and bridging the diverse terms used in the literature. In doing so, we further establish important connections between shortcuts and related fields, including bias, causality, and security, where parallels exist but are rarely discussed. Our taxonomy organizes existing approaches for shortcut detection and mitigation, providing a comprehensive overview of the current state of the field and revealing underexplored areas and open challenges. Moreover, we compile and classify datasets tailored to study shortcut learning. Altogether, this work provides a holistic perspective to deepen understanding and drive the development of more effective strategies for addressing shortcuts in machine learning.