Spurious Correlation Robustness

Ask about this topic

Overview

This field studies how models can avoid relying on shortcuts—such as backgrounds, demographic attributes, or writing patterns—that correlate with labels in training data but may change at deployment. Common approaches include group-robust objectives and reweighting, counterfactual data generation, invariant or disentangled representations, and methods that identify shortcut features through explanations or model internals. Researchers evaluate these methods across vision, text, medical, and structured-data tasks, often using worst-group accuracy and out-of-distribution tests alongside average accuracy. A central challenge is reducing harmful reliance without discarding context that carries useful signal, especially when subgroup labels or representative validation data are scarce.

Latest papers

CardsList

63 papers7 papers in the last four weeks, up 40% on the four weeks before. 0.0% of all new papers.

  1. Selective Tie Learning: Mitigating Spurious Correlations in Preference Optimization

    Oct 26, 2026Christian Moya, Purav Matlia, Elliott Thornley +1Preference OptimizationSpurious Correlation Robustness

    Purdue University · National University of Singapore

  2. Do Similarity Measures Measure Similarity? How User Activity Creates Phantom Correlation in Recommender Systems

    Oct 26, 2026Marco Favier, Noah Daniëls, Jens Leysen +2Spurious CorrelationCollaborative Filtering

    University of Antwerp, Belgium

  3. Semantic Concept Steering Breaks the Explanation Drift Loop in Continual Learning

    Oct 24, 2026Yehonatan Elisha, Oren Barkan, Noam KoenigsteinRegularization-Based Continual LearningSpurious Correlation Robustness

    Tel Aviv University · The Open University

  4. Interpreting Supervised Pairwise Graph Representations: Local Evidence, Confounding, and Provable Post-hoc Correction

    Oct 23, 2026Ilya Brekin, Ariela Moldavskaya, Elina Sidorova +1Graph Representation LearningSpurious Correlation Robustness

    HSE University, Moscow, Russia · Technion – Israel Institute of Technology, Technion City, Haifa 3200003, Israel · Lomonosov Moscow State University, Moscow, Russia +1

  5. BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance

    Oct 5, 2026Haojin Deng, Zhiping Lin, Yimin YangDebiased MLSpurious Correlation Robustness

    Vector Institute, Toronto, Canada

  6. Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise

    Oct 1, 2026Sung Ho Jo, Seonghwi Kim, Wonsang Yun +1Distribution Shift RobustnessSpurious Correlation Robustness

    Pohang University of Science and Technology (POSTECH)

  7. Towards Fast and Disentangled Counterfactuals for Visual Foundation Models

    Oct 1, 2026Sidney Bender, Benedikt Kunz, Ahmed Zeid +3Disentangled Representation LearningCounterfactual Explanations

    Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Germany · Machine Learning Group, Technische Universität Berlin, Berlin, Germany

  8. When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic

    Sep 30, 2026Muhammad Zawish, Steven DavyVLM RobustnessEfficient VLM Inference

    Technological University Dublin, Ireland

  9. Whitening Improves Robustness to Spurious Correlations in Linear Probes

    Sep 30, 2026Floris Holstege, Bram Wouters, Noud van Giersbergen +1Linear ProbingFeature Whitening

    University of Amsterdam, Department of Quantitative Economics · Tinbergen Institute

  10. Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification

    Sep 23, 2026Ilán Carretero, Pablo Meseguer, Rocío del Amor +1Batch Effect CorrectionPathology Foundation Models

    CVBLab, HumanTech, Universitat Politècnica de València (UPV), Valencia, Spain · Artikode Intelligence S.L., Valencia, Spain

  11. Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables

    Sep 9, 2026Yasin Ibrahim, Hermione Warr, Robin J. Evans +1Counterfactual EvaluationClassification

    Department of Engineering Science, University of Oxford, Oxford, UK · Department of Statistics, University of Oxford, Oxford, UK

  12. "World Knowledge" in the Weights: Reading Concept Circuits of Vision Transformers

    Sep 8, 2026Yanlin Chen, Tang Li, Xi PengTransformer InterpretabilityVision Foundation Models

    Department of Computer & Information Sciences, University of Delaware, USA · Department of Computer Science, University of Virginia, USA

  13. SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations

    Sep 1, 2026Yiming Luo, Rongqiang Zhao, Jie LiuDistribution Shift RobustnessSynthetic Data Augmentation

    1Harbin Institute of Technology · 2State Key Laboratory of Smart Farm Technologies and Systems

  14. TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification

    Aug 31, 2026Ze Chen, Qiming Yu, Zijia Song +2Memory-Augmented Neural NetworksDisentangled Representation Learning

    National University of Defense Technology Hefei, Anhui, China

  15. Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction

    Aug 27, 2026Jin Mu, Guanhua ChenLanguage Model RobustnessLanguage Model Auditing

    University of Wisconsin–Madison

  16. Hull First, Wake Second: Wake-Reliance Suppression for Robust Maritime Vessel Detection

    Aug 27, 2026Yefan Wang, Xingyu Wang, Ruibiao Zhu +1Ship DetectionObject Detection

    University of Shanghai for Science and Technology, Shanghai, China · University of Science and Technology Liaoning, Liaoning, China · School of Computing, College of Systems and Society, The Australian National University, ACT, Australia +1

  17. AT-ViT: Area-Targeted Multi-View Vision Transformer with Cross-Attention and Multi-Scale Patching for Plant Trait Recognition in Herbarium Images

    Aug 21, 2026Amani Sedrat, Takieddine Chehhat, Youcef Sklab +5Vision TransformerPlant Phenotyping

    Laboratoire LITAN, École supérieure en Sciences et Technologies de l’Informatique et du Numérique RN 75, Amizour 06300, Béjaïa, Algérie · IRD, Sorbonne Université, UMMISCO, Paris, France · Institut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, 75013 Paris, France

  18. False-science induction in autonomous scientific discovery

    Aug 20, 2026Hanbing Liang, Fujun LiuAutonomous ExperimentationSpurious Correlation Robustness

    Nanophotonics and Biophotonics Key Laboratory of Jilin Province, School of Physics, Changchun University of Science and Technology, Changchun 130022, P.R. China

  19. SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imaging

    Aug 18, 2026Shenhav Nadir, Meir Yossef Levi, Eyal Gofer +1Spurious Correlation RobustnessSupervised Contrastive Learning

    Viterbi Faculty of Electrical and Computer Engineering, Technion - Israel Institute of Technology

  20. ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning

    Aug 13, 2026Qianqian Wang, Yunshan Li, Dawei Huang +2Distribution Shift RobustnessSpurious Correlation Robustness

    aShenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet, Shenzhen, China · bDepartment of Statistics and Data Science, Southern University of Science and Technology, Shenzhen, China

  21. UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers

    Aug 10, 2026Chidaksh Ravuru, Shashank SrivastavaClassificationSpurious Correlation Robustness

    Department of Computer Science University of North Carolina, Chapel Hill

  22. Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples

    Aug 5, 2026Nilesh KumarTraining Data SelectionClassification

  23. Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners

    Jul 28, 2026Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz +1Spurious Correlation RobustnessTabular ICL

    Hologen AI London, UK · Mathematics Research Centre Academy of Athens Athens, GR · FAU Erlangen Nuremberg Imperial College London Erlangen, DE & London, UK +1

  24. Causal-Adversarial Probing of Clinical Covariates for Prostate MRI Grading

    Jul 16, 2026Yipei Wang, Shiqi Huang, Wen Yan +6Causal Representation LearningMedical Image Classification

    UCL Hawkes Institute, University College London, London, UK · Department of Medical Physics and Biomedical Engineering, University College London, London, UK · Department of Urology, University College London Hospital, London, UK +4

  25. When Data Imbalance Helps: Robust Generalization Through Shortcut Saturation

    Jul 11, 2026Cheng-Ting Chou, Duc Binh HoangClass-Imbalanced LearningTransformer

    University of California, Los Angeles

  26. Breaking Spurious Correlations via Generative Randomization and Cross-Variant Self-Supervised Learning

    Jul 7, 2026Suraj Yadav, Anjaneya Sharma, Siddharth YadavContrastive LearningGroup Distributionally Robust Optimization

    Indraprastha Institute of Information Technology Delhi

  27. Association Restoration Test: Revealing Restorable Shortcuts after Unlearning

    Jul 7, 2026Amy Lu, Changxiu JiSpurious Correlation RobustnessShortcut Learning

    Department of Computer Science, Stanford University

  28. Adversarial LassoNet: Robust Feature Selection via Stability-Driven Sparse Learning

    Jul 4, 2026Zhen Huang, Peicheng Xu, Junbiao Pang +1Adversarial TrainingOOD Generalization

    Beijing University of Technology · The First Affiliated Hospital of Zhejiang University School of Medicine

  29. Automated Background Swapping for Robustness against Spurious Backgrounds

    Jun 30, 2026Cesar Roder, Kajetan SchweighoferSynthetic Data AugmentationData Augmentation

    Johannes Kepler University Linz, Austria · Cognizant AI Lab, USA ∗ · ∗Work partly done while at Johannes Kepler University Linz, Austria

  30. Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement

    Jun 23, 2026Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu +5Disentangled Representation LearningDebiased ML

    Xidian University · Shaanxi, China · Microsoft Research Asia +1