mlsanityData to 14 Oct 2026

Aequitas: A Bias and Fairness Audit Toolkit

arXiv 1811.05577 ↗First posted 14 Nov 2018cs.LG cs.AI cs.CYcited by 147

Not on the map. Why?

Abstract (arXiv)

Recent work has raised concerns on the risk of unintended bias in AI systems being used nowadays that can affect individuals unfairly based on race, gender or religion, among other possible characteristics. While a lot of bias metrics and fairness definitions have been proposed in recent years, there is no consensus on which metric/definition should be used and there are very few available resources to operationalize them. Therefore, despite recent awareness, auditing for bias and fairness when developing and deploying AI systems is not yet a standard practice. We present Aequitas, an open source bias and fairness audit toolkit that is an intuitive and easy to use addition to the machine learning workflow, enabling users to seamlessly test models for several bias and fairness metrics in relation to multiple population sub-groups. Aequitas facilitates informed and equitable decisions around developing and deploying algorithmic decision making systems for both data scientists, machine learning researchers and policymakers.

Key facts. Cited by 147 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 26; 2023: 26; 2024: 39; 2025: 22; 2026: 16.

147 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 207
  2. 2023Auditing large language models: a three-layered approachcited by 137
  3. 2021Trustworthy AI: A Computational Perspectivecited by 93
  4. 2023Fast Model Debias with Machine Unlearningcited by 72
  5. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 58
  6. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  7. 2023Understanding accountability in algorithmic supply chainscited by 40
  8. 2022Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkitscited by 34
  9. 2022A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithmscited by 30
  10. 2022Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Modelscited by 30
  11. 2024Farsight: Fostering Responsible AI Awareness During AI Application Prototypingcited by 28
  12. 2022FairGBM: Gradient Boosting with Fairness Constraintscited by 25
38 more
  1. 2021Testing Group Fairness via Optimal Transport Projectionscited by 23
  2. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  3. 2022The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairnesscited by 21
  4. 2022De-biasing "bias" measurementcited by 20
  5. 2023Statistical Inference for Fairness Auditingcited by 20
  6. 2023Bias and Fairness in Chatbots: An Overviewcited by 20
  7. 2021Conformity Assessments and Post-market Monitoring: A Guide to the Role of Auditing in the Proposed European AI Regulationcited by 19
  8. 2021A Framework for Fairness: A Systematic Review of Existing Fair AI Solutionscited by 18
  9. 2023The Possibility of Fairness: Revisiting the Impossibility Theorem in Practicecited by 18
  10. 2021Promoting Fairness through Hyperparameter Optimizationcited by 17
  11. 2021Towards the Right Kind of Fairness in AIcited by 15
  12. 2024FairAIED: Navigating Fairness, Bias, and Ethics in Educational AI Applicationscited by 15
  13. 2021Learning from Multiple Noisy Partial Labelerscited by 14
  14. 2022DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systemscited by 14
  15. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
  16. 2022System Cards for AI-Based Decision-Making for Public Policycited by 13
  17. 2021Demographic Fairness in Biometric Systems: What do the Experts say?cited by 12
  18. 2022A Sandbox Tool to Bias(Stress)-Test Fairness Algorithmscited by 12
  19. 2022Towards a multi-stakeholder value-based assessment framework for algorithmic systemscited by 12
  20. 2024OxonFair: A Flexible Toolkit for Algorithmic Fairnesscited by 12
  21. 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challengescited by 12
  22. 2021SoK: Machine Learning Governancecited by 10
  23. 2023Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harmscited by 10
  24. 2024Auditing of AI: Legal, Ethical and Technical Approachescited by 10
  25. 2021fairmodels: A Flexible Tool For Bias Detection, Visualization, And Mitigationcited by 9
  26. 2024Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMscited by 9
  27. 2021BeFair: Addressing Fairness in the Banking Sectorcited by 8
  28. 2021An Empirical Comparison of Bias Reduction Methods on Real-World Problems in High-Stakes Policy Settingscited by 8
  29. 2022VisCUIT: Visual Auditor for Bias in CNN Image Classifiercited by 8
  30. 2022Recommendations on test datasets for evaluating AI solutions in pathologycited by 8
  31. 2024ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methodscited by 8
  32. 2024Feature Responsiveness Scores: Model-Agnostic Explanations for Recoursecited by 8
  33. 2022Fairness Implications of Encoding Protected Categorical Attributescited by 7
  34. 2022Bias and unfairness in machine learning models: a systematic literature reviewcited by 7
  35. 2023Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairnesscited by 7
  36. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  37. 2024Fairness in Large Language Models in Three Hourscited by 7
  38. 2024Secure and Confidential Certificates of Online Fairnesscited by 7

50 most cited of 147 All 147 (JSON)