mlsanityData to 14 Oct 2026

A Survey on Bias and Fairness in Machine Learning

arXiv 1908.09635 ↗First posted 23 Aug 2019cs.LGcited by 1,917

Not on the map. Why?

Cited by 36 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

With the widespread use of AI systems and applications in our everyday lives, it is important to take fairness issues into consideration while designing and engineering these types of systems. Such systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that the decisions do not reflect discriminatory behavior toward certain groups or populations. We have recently seen work in machine learning, natural language processing, and deep learning that addresses such challenges in different subdomains. With the commercialization of these systems, researchers are becoming aware of the biases that these applications can contain and have attempted to address them. In this survey we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined in order to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and how they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.

Key facts. Cited by 1,917 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 224; 2022: 371; 2023: 411; 2024: 397; 2025: 346; 2026: 168.

1,917 papers.

Sort:

By area:

  1. 2021Ethical and social risks of harm from Language Modelscited by 966
  2. 2021Learning to Prompt for Continual Learningcited by 944
  3. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  4. 2021Carbon Emissions and Large Neural Network Trainingcited by 567
  5. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  6. 2021Towards Personalized Federated Learningcited by 464
  7. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 412
  8. 2022A Survey of Machine Unlearningcited by 312
  9. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
  10. 2022Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learntcited by 236
  11. 2022Challenges and Strategies in Cross-Cultural NLPcited by 218
  12. 2021Trustworthy AI: From Principles to Practicescited by 207
38 more
  1. 2023Data-centric Artificial Intelligence: A Surveycited by 203
  2. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  3. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  4. 2024Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuningcited by 177
  5. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  6. 2021Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Trainingcited by 166
  7. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  8. 2021A survey on datasets for fairness-aware machine learningcited by 157
  9. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 156
  10. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 151
  11. 2023Debiasing Vision-Language Models via Biased Promptscited by 149
  12. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 148
  13. 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 146
  14. 2023Auditing large language models: a three-layered approachcited by 137
  15. 2022Training Data Influence Analysis and Estimation: A Surveycited by 135
  16. 2022Continual Learning and Private Unlearningcited by 130
  17. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Modelscited by 130
  18. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  19. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  20. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  21. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 120
  22. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 118
  23. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  24. 2021Gender Bias in Machine Translationcited by 117
  25. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  26. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  27. 2021Re-imagining Algorithmic Fairness in India and Beyondcited by 104
  28. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  29. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  30. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  31. 2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 98
  32. 2024NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samplescited by 97
  33. 2023A Survey on Fairness in Large Language Modelscited by 95
  34. 2021Trustworthy AI: A Computational Perspectivecited by 93
  35. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  36. 2022DataPerf: Benchmarks for Data-Centric AI Developmentcited by 90
  37. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 90
  38. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89

50 most cited of 1,917 All 1,917 (JSON)