mlsanityData to 14 Oct 2026

Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer

arXiv 1711.06664 ↗First posted 17 Nov 2017stat.ML cs.LGcited by 233

Not on the map. Why?

Abstract (arXiv)

In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version of this interaction with a two-stage framework containing an automated model and an external decision-maker. The model can choose to say "Pass", and pass the decision downstream, as explored in rejection learning. We extend this concept by proposing "learning to defer", which generalizes rejection learning by considering the effect of other agents in the decision-making process. We propose a learning algorithm which accounts for potential biases held by external decision-makers in a system. Experiments demonstrate that learning to defer can make systems not only more accurate but also less biased. Even when working with inconsistent or biased users, we show that deferring models still greatly improve the accuracy and/or fairness of the entire system.

Key facts. Cited by 233 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 25; 2023: 29; 2024: 39; 2025: 42; 2026: 81.

233 papers.

Sort:

By area:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2021Machine Learning with a Reject Option: A surveycited by 109
  3. 2022CARD: Classification and Regression Diffusion Modelscited by 103
  4. 2025Universal Model Routing for Efficient LLM Inferencecited by 86
  5. 2021Differentiable Learning Under Triagecited by 76
  6. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 72
  7. 2023Who Should Predict? Exact Algorithms For Learning to Defer to Humanscited by 70
  8. 2022Calibrated Learning to Defer with One-vs-All Classifierscited by 69
  9. 2023Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Makingcited by 67
  10. 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 60
  11. 2023When Does Confidence-Based Cascade Deferral Suffice?cited by 60
  12. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
38 more
  1. 2023In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Makingcited by 50
  2. 2026Building Production-Ready Probes For Geminicited by 47
  3. 2022Sample Efficient Learning of Predictors that Complement Humanscited by 46
  4. 2022Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairnesscited by 45
  5. 2025Magentic-UI: Towards Human-in-the-loop Agentic Systemscited by 43
  6. 2021Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibrationcited by 40
  7. 2022Forming Effective Human-AI Teams: Building Machine Learning Models that Complement the Capabilities of Multiple Expertscited by 40
  8. 2023Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithmscited by 36
  9. 2021Role of Human-AI Interaction in Selective Predictioncited by 35
  10. 2024Complementarity in Human-AI Collaboration: Concept, Sources, and Evidencecited by 35
  11. 2022On the Utility of Prediction Sets in Human-AI Teamscited by 34
  12. 2022Who Goes First? Influences of Human-AI Workflow on Decision Making in Clinical Imagingcited by 32
  13. 2023Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstentioncited by 32
  14. 2021Teaching Humans When To Defer to a Classifier via Exemplarscited by 29
  15. 2024Regression with Multi-Expert Deferralcited by 29
  16. 2021Classification with abstention but without disparitiescited by 28
  17. 2024Learning to Defer to a Population: A Meta-Learning Approachcited by 27
  18. 2024Evaluating Human-AI Collaboration: A Review and Methodological Frameworkcited by 27
  19. 2022Uncalibrated Models Can Improve Human-AI Collaborationcited by 26
  20. 2023In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defercited by 26
  21. 2023Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Makingcited by 25
  22. 2023Learning to Defer with Limited Expert Predictionscited by 25
  23. 2023When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programmingcited by 25
  24. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  25. 2022A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementaritycited by 23
  26. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  27. 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboardingcited by 20
  28. 2025Conformal Linguistic Calibration: Trading-off between Factuality and Specificitycited by 20
  29. 2021Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possiblecited by 19
  30. 2022Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservablescited by 19
  31. 2022Learning When to Advise Human Decision Makerscited by 18
  32. 2021Leveraging Expert Consistency to Improve Algorithmic Decision Supportcited by 17
  33. 2021Incorporating Uncertainty in Learning to Defer Algorithms for Safe Computer-Aided Diagnosiscited by 17
  34. 2024A Two-Stage Learning-to-Defer Approach for Multi-Task Learningcited by 17
  35. 2022Human-AI Collaboration in Decision-Making: Beyond Learning to Defercited by 16
  36. 2024On Subjective Uncertainty Quantification and Calibration in Natural Language Generationcited by 16
  37. 2024Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Modelscited by 16
  38. 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guaranteescited by 16

50 most cited of 233 All 233 (JSON)