mlsanityData to 14 Oct 2026

Counterfactual Fairness

arXiv 1703.06856 ↗First posted 20 Mar 2017stat.ML cs.CY cs.LGcited by 804

Not on the map. Why?

Abstract (arXiv)

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it is the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.

Key facts. Cited by 804 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 125; 2022: 161; 2023: 157; 2024: 119; 2025: 129; 2026: 113.

804 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  2. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  3. 2023LEACE: Perfect linear concept erasure in closed formcited by 267
  4. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  5. 2024ShieldGemma: Generative AI Content Moderation Based on Gemmacited by 243
  6. 2021Towards Causal Representation Learningcited by 209
  7. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 178
  8. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 173
  9. 2021A survey on datasets for fairness-aware machine learningcited by 157
  10. 2023Auditing large language models: a three-layered approachcited by 137
  11. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  12. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
38 more
  1. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  2. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  3. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  4. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  5. 2021Trustworthy AI: A Computational Perspectivecited by 93
  6. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  7. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  8. 2021Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Searchcited by 90
  9. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  10. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  11. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  12. 2022Distilling Model Failures as Directions in Latent Spacecited by 82
  13. 2024Robust agents learn causal world modelscited by 81
  14. 2021Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Testscited by 77
  15. 2022Fairness in Graph Mining: A Surveycited by 76
  16. 2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
  17. 2021Fair Conformal Predictors for Applications in Medical Imagingcited by 74
  18. 2021Mitigating Political Bias in Language Models Through Reinforced Calibrationcited by 73
  19. 2023Fast Model Debias with Machine Unlearningcited by 72
  20. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  21. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  22. 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
  23. 2021AutoDebias: Learning to Debias for Recommendationcited by 68
  24. 2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 68
  25. 2022A Systematic Study of Bias Amplificationcited by 65
  26. 2021Fairness via Representation Neutralizationcited by 63
  27. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  28. 2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58
  29. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  30. 2021DORO: Distributional and Outlier Robust Optimizationcited by 56
  31. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  32. 2021Directional Bias Amplificationcited by 54
  33. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  34. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 52
  35. 2021Agent Incentives: A Causal Perspectivecited by 51
  36. 2022Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigationcited by 51
  37. 2023Causal normalizing flows: from theory to practicecited by 51
  38. 2025Do-PFN: In-Context Learning for Causal Effect Estimationcited by 51

50 most cited of 804 All 804 (JSON)