Counterfactual Data Augmentation

Ask about this topic

Overview

Counterfactual data augmentation studies how to create training examples that change a meaningful factor—such as an image region, sentence meaning, or object position—while keeping other relevant information stable. Common approaches use generative models, language models, causal models, or minimal rule-based edits, then train with contrastive, supervised, or preference-based objectives. The methods are used to address scarce or imbalanced data, reduce reliance on spurious correlations, and improve robustness, fairness, and generalization in settings from medical imaging to robotics and language. A central challenge is ensuring that edits are realistic and change only the intended factor; poorly controlled examples or excessive augmentation can hurt performance, so validation and augmentation dose remain important.

Latest papers

CardsList

38 papers8 papers in the last four weeks, up 167% on the four weeks before. 0.0% of all new papers.

  1. CFBrainAug: Modularity-Induced Counterfactual Brain Network Augmentation for Interpretable fMRI-based Autism Diagnosis

    Oct 23, 2026Yifan Qiao, Sheng LiCounterfactual Data AugmentationBrain Network Analysis

    University of Virginia, Charlottesville, VA, USA

  2. Pos4CHD: A Positive-Free Mask-Guided Counterfactual Synthesis Framework for Fetal Congenital Heart Defect Analysis

    Oct 22, 2026Wenjie Xuan, Yapeng Li, Hang Su +5Medical Image SynthesisSynthetic Anomaly Generation

  3. Cartender: Verifiable Language-Conditioned Driving by Learning the Drives Not Taken

    Oct 19, 2026Zhiwen Chen, Benjin Zhu, Yan Xie +1Instruction Generalization in VLA ModelsTrajectory Generation

    The Hong Kong University of Science and Technology (hkust-gz.edu.cn) · Li Auto Inc. (lixiang.com) · The Hong Kong University of Science and Technology (ust.hk)

  4. ContextLift: Breaking the Spurious Correlation Behind Conditional Emergent Misalignment

    Oct 15, 2026Florian Mai, David KaczérEmergent Misalignment in Language ModelsLLM Safety Alignment

    Bonn-Aachen International Center for Information Technology, University of Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Germany

  5. Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification

    Oct 8, 2026Inês Cruchinho Garcia, Mariana Mourão, Francisco Maria Calisto +2Mammography Image ClassificationCounterfactual Data Augmentation

    Institute for Systems and Robotics, Instituto Superior Técnico, Lisbon, Portugal

  6. Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs

    Sep 30, 2026Taegeun Yang, Youngju Na, Yoonki Cho +1Vision-Language-Action ModelsCounterfactual Data Augmentation

    Korea Advanced Institute of Science and Technology (KAIST)

  7. When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models

    Sep 30, 2026Hung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen +4Robotic ManipulationVision-Language-Action Models

    National Tsing Hua University · National Taiwan University

  8. Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents

    Sep 29, 2026Jianchang Su, Yiwei Yang, Wei ZhangAutomated Fact-CheckingLLM Reliability

    University of Connecticut · University of California, Santa Cruz

  9. Pulseflow: PPG Counterfactual Generation Via Latent Transport

    Sep 27, 2026Hung Manh Pham, Dong Ma, Bin Zhu +1Atrial Fibrillation DetectionCounterfactual Data Augmentation

    University of Cambridge, United Kingdom

  10. MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution

    Sep 17, 2026Loan Bernat, Matthieu Grard, Ariane Herbulot +1Long-Horizon Robotic ManipulationRobot Failure Recovery

    LAAS-GEPETTO · LAAS-RAP

  11. To do(xx) or not to do(xx): Medical Image Counterfactuals for Dataset Augmentation

    Sep 12, 2026Yasin Ibrahim, Robin J. Evans, Konstantinos KamnitsasFairness in Medical Image ClassificationCounterfactual Data Augmentation

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

  12. RePair: Turning Retrieval Failures into Counterfactual Hard Pairs

    Aug 30, 2026Siyi Liu, Xiaorong Zhu, Enjun Du +6Cross-Modal RetrievalCounterfactual Data Augmentation

    The Hong Kong University of Science and Technology (Guangzhou) · Tencent Yuanbao · The University of Hong Kong +1

  13. DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs

    Aug 4, 2026Jian Zhang, Bingyi Wang, Yizhi LiuRL for Language Model ReasoningCausal Reasoning in Language Models

    Zhejiang University

  14. Static In, Dynamic Out: Counterfactual Action Augmentation for Moving Object Manipulation

    Jul 30, 2026Woo Chul Shin, Zhenyang Chen, Alfred Cueva +5Robot Policy AdaptationVisuomotor Policy Learning

    Georgia Institute of Technology

  15. SPARC Segmentation to Prediction via Affine Regression and Counterfactuals

    Jul 28, 2026Shivani, Subhayan RoyClass-Imbalanced LearningCounterfactual Data Augmentation

  16. Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification

    Jul 23, 2026Kritanu Chattopadhyay, Sayanjit Singha Roy, Soumya ChatterjeeCounterfactual ExplanationsMedical Image Classification

    Department of Mechanical Engineering, National Institute of Technology Durgapur, West Bengal, 713209, India · Department of Electrical Engineering, IIT Kanpur, Uttar Pradesh, 208016, India · Department of Electrical Engineering, National Institute of Technology Durgapur, West Bengal, 713209, India

  17. Improving Rare Medication Recommendation with Counterfactual Data Augmentation and Large Language Models

    Jul 23, 2026Shinhwan Kang, Soo Yong Lee, Jaewon Kim +2Medication RecommendationClinical Decision Support

    KAIST Seoul, South Korea · KAIST Daejeon, South Korea · Korea University Seoul, South Korea

  18. Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysis

    Jul 15, 2026S M Rafiuddin, Vamsi Krishna Pavuluri, Atriya SenCounterfactual EvaluationCounterfactual Explanations

    Department of Computer Science, Oklahoma State University, Stillwater, Oklahoma, USA

  19. 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

  20. CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness

    Jul 1, 2026Xinyu Jia, Weidong Guo, Wangyuan Zhao +3Algorithmic FairnessMedical Image Synthesis

    College of Biomedical Engineering, Fudan University, Shanghai, China

  21. Counterfactual Residual Data Augmentation for Regression

    Jun 26, 2026Hossein Mohebbi, Oliver Schulte, Ke Li +1Synthetic Tabular Data GenerationCounterfactual Data Augmentation

    University of Waterloo · Vector Institute · Simon Fraser University.

  22. CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correction

    Jun 13, 2026Qianyu Wang, Xiaoman Wang, Yuanyuan Liang +2Grammatical Error CorrectionCounterfactual Data Augmentation

    East China Normal University

  23. LLM Explainability with Counterfactual Chains and Causal Graphs

    Jun 4, 2026Nirit Nussbaum-Hoffer, Nitay Calderon, Liat Ein-Dor +1LLM Reasoning with GraphsLLM Interpretability

    Faculty of Data and Decision Sciences, Technion · IBM Research

  24. Stance Detection in Prediction Markets: Addressing Imbalanced Trader Commentary via Counterfactual Augmentation and Market Context

    May 27, 2026Thomas MbriceClass-Imbalanced LearningStance Detection

    Department of Computer Science Stony Brook University

  25. TypedCSIP: Typed Counterfactual Pretraining for Chinese Legislative Conflict Classification

    May 25, 2026Yao LiuLegal NLPClassification

    Chengdu University of Technology, Leshan, China

  26. When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection

    May 25, 2026Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz +2Counterfactual Data AugmentationAnomaly Detection

    School of Electrical Engineering and Robotics, Faculty of Engineering, −Queensland University of Technology, Brisbane, Queensland, Australia

  27. Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding

    May 11, 2026Jianzhu Bao, Haozhen Zhang, Kuicai Dong +5Data VisualizationVLM Adaptation

    1Nanyang Technological University · 2Aumovio Singapore Pte. Ltd.

  28. Verifiable Counterfactual Supervision for Process Reward Models

    May 4, 2026Yinghui Chi, Yuanhong WangProcess Reward ModelsProcess Supervision

    Jilin University

  29. Counterfactual Peptide Editing for Causal TCR--pMHC Binding Inference

    Apr 14, 2026Sanjar Khudoyberdiev, Arman BekovCounterfactual Data AugmentationCausal Inference

  30. Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization

    Apr 9, 2026Simon Zhang, Ryan P. DeMilt, Kun Jin +1OOD GeneralizationCovariate Shift

    Department of Computer Science, Purdue University, West Lafayette, USA · Department of Computer Science and Engineering, The Ohio State University, Columbus Ohio, USA · Department of Industrial and Systems Engineering, The Ohio State University, Columbus Ohio, USA