AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
The DOI matches its Crossref record; 28 of the 31 references it cites were found in a registry or an index.
Abstract
Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This article introduces a new open-source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license (https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms for use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience that provides a gentle introduction to the concepts and capabilities for line-of-business users, researchers, and developers to extend the toolkit with their new algorithms and improvements and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the Linux Foundation, which hosts several of the open source tools we found (IBM's AI Fairness 360 [15], for example).”
From Towards AI Accountability Infrastructure: Gaps and Opportunities in AI Audit Tooling (2025) · cites this paper as [15]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“An open-source toolkit, the AI Fairness 360, is available to help AI researchers examine, report, and mitigate discrimination and bias in machine learning models throughout the AI development lifecycle [52].”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [52]
The cited source says what the claim attributes to it.
In the citing paper
“It includes a comprehensive set of metrics for datasets and models to test for biases, explanations for those metrics, and algorithms to mitigate bias in datasets and models.”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [52]
The cited source says what the claim attributes to it.
In the citing paper
“If bias is discovered in an algorithm, a variety of solutions are now available to help mitigate and reduce the level of bias (Bellamy et al., 2019).”
From Addressing Fairness, Bias, and Appropriate Use of Artificial Intelligence and Machine Learning in Global Health (2021) · cites this paper as Bellamy et al., 2019
The cited source says what the claim attributes to it.
In the citing paper
“Various toolboxes have been released in the past years to assist the algorithm experimentation and software development to enhance AI trustworthiness in different aspects such as fairness [12, 13, 71], XAI [56, 1, 8], and adversarial robustness [55, 2].”
From Trustworthy AI: From Principles to Practices (2023) · cites this paper as [12]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,410
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536
Certifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Mitigating Unwanted Biases with Adversarial Learning
Zhang, B. H., Lemoine, B., & Mitchell, M. (2018) · Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3278721.3278779 · Cited by 1,387
Data preprocessing techniques for classification without discrimination
Kamiran, F., & Calders, T. (2012) · Knowledge and Information Systems · doi:10.1007/s10115-011-0463-8 · Cited by 1,305
(2013) · Cited by 1,126
Counterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
Kusner, M. J., Loftus, J. R., Russell, C., & Silva, R. (2017) · arXiv · doi:10.48550/arxiv.1703.06856 · Cited by 995
Optimized Pre-Processing for Discrimination Prevention
Calmon, F. P., Wei, D., Vinzamuri, B., Ramamurthy, K. N., & Varshney, K. R. (2017) · neural information processing systems · Cited by 978
Self-citationInherent trade-offs in the fair determination of risk scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2017) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2017.43 · Cited by 943
Research works printed but not linked: 4
- Kohavi, R. Scaling up the accuracy of naive-Bayes classifiers: a decision-tree hybrid. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining , 1996. URL https://archive. ics.uci.edu/ml/datasets/adult .
- Kusner, M. J., Loftus, J. R., Russell, C., and Silva, R. Counterfactual fairness. In NIPS , 2017.
- bellamy, 2018, AI Fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias, arXiv 1810 01943
- Narayanan, A. Translation tutorial: 21 fairness definitions and their politics. In Conference on Fairness, Accountability, and Transparency , February 2018.
Cited by
Items 801–900 of 1,009
Monitoring bias and fairness in machine learning models: A reviewPreprint
Bacelar, M. (2021) · doi:10.14293/s2199-1006.1.sor-.pp59wrh.v1 · Cited by 12
Singh, M., GHALACHYAN, G., Varshney, K. R., & Bryant, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.14653 · Cited by 12
Self-citationProvable Fairness for Neural Network Models using Formal VerificationPreprint
Borca‐Tasciuc, G., Guo, X., Bak, S., & Skiena, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.08578 · Cited by 9
Koumeri, L. K., Legast, M., Yousefi, Y., Vanhoof, K., Legay, A., & Schommer, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.08394 · Cited by 13
How Could AI Support Design Education? A Study Across Fields Fuels Situating AnalyticsPreprint
Jain, A., Kerne, A., Fowler, H., Seo, J. H., Newman, G., Lupfer, N., & Perrine, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.17390 · Cited by 12
Aequitas Flow: Streamlining Fair ML ExperimentationPreprint
de Jesus, S. H. C., Saleiro, P., Silva, I. O. E., Jorge, B. M., Ribeiro, R. P., da Gama, J. M. P., Bizarro, P., & Ghani, R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.05809 · Cited by 14
Barr, C. J. S., Erdélyi, O. J., Docherty, P. D., & Grace, R. C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.06624 · Cited by 11
LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
Bouchard, D., Chauhan, M. S., Skarbrevik, D., Bajaj, V., & Ahmad, Z. (2025) · The Journal of Open Source Software · doi:10.21105/joss.07570 · Cited by 12
Chandra, J., & Navneet, S. K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.15901 · Cited by 13
Catalog of General Ethical Requirements for AI CertificationPreprint
Corrêa, N. K., & Mönig, J. M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.12289 · Cited by 11
Detecting Systematic Deviations in Data and Models
Speakman, S., Tadesse, G. A., Cintas, C., Ogallo, W., Akumu, T., & Oshingbesan, A. (2023) · Computer · doi:10.1109/mc.2022.3213209 · Cited by 9
STILE: Exploring and Debugging Social Biases in Pre-trained Text Representations
Kabir, S., Li, L., & Zhang, T. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642111 · Cited by 8
Wankhade, S., Sahni, M., León‐Castro, E., & Olazabal-Lugo, M. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1535845 · Cited by 12
“A notable case is IBM’s AI Fairness 360 toolkit, which has been used to audit healthcare models for gender bias (Bellamy et al., 2019).”
Longitudinal Prediction of Mental Health Outcomes in Vulnerable Youth using Machine Learning
Pujadas, E. R., Díaz‐Caneja, C. M., Stevanović, D., Ferrer-Quintero, M., Martín-Isla, C., Hernández-González, J., Atehortúa, A., Lazrak, N., Pries, L.-K., Delespaul, P., et al. (2025) · Cognitive Computation · doi:10.1007/s12559-025-10509-y · Cited by 9
“In this work, the IBM 360 fairness library (version 0.5.0) was utilized to detect unfair biases in the models [45].”
InfluentialBalancing Act: Early, Fair, and Accurate Identification of At-Risk Students
Cheng, A. S., Pei, B., & Liu, C. (2025) · Journal of Learning Analytics · doi:10.18608/jla.2025.8761 · Cited by 9
Navigating Uncertainties: How GenAI Developers Document Their Models on Open-Source Platforms
Tang, N., Li, M., Winecoff, A., Madaio, M., Heidari, H., & Shen, H. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790910 · Cited by 9
“Such resources could include lightweight bias evaluation protocols (similar in spirit to AI Fairness 360 [9] or Fairlearn [123]) and standardized red-teaming templates [cf. 39].”
Agentic AI in Branding: Driving Hyper-personalization and Real-time Adaptation
Puri, S., Pradhan, J. A., Bernabe, B. G., & Ray, A. (2026) · Global Business Review · doi:10.1177/09721509251414773 · Cited by 10
Cachel, K., & Rundensteiner, E. A. (2022) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3514094.3534160 · Cited by 10
Danner, M., Hadžić, B., Weber, T., Zhu, X., & Rätsch, M. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-39059-3_21 · Cited by 8
Achieving counterfactual fairness with imperfect structural causal model
Duong, T. D., Li, Q., & Xu, G. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122411 · Cited by 9
Justicia algorítmica: un enfoque sociotécnico
Bolado, A. B. (2023) · Estudios Penales y Criminológicos · doi:10.15304/epc.44.8838 · Cited by 11
Rahimi, P., Ecabert, C., & Marce, S. (2023) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb57857.2023.10449046 · Cited by 11
“Pre-processing approaches involve modifying the input data to remove or reduce the effects of bias [26, 41, 4].”
MethodGuardians of the Algorithm: Human Oversight in the Ethical Evolution of AI and Data Analysis
Dwivedi, D. N., & Mahanty, G. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-2964-1.ch012 · Cited by 8
HR in the Era of AI Paradoxes: Balancing Automation and Human Touch
Suneetha, S., Sudheer, A. K., Shankar, C., & Metta, S. (2024) · Advances in economics, business and management research/Advances in Economics, Business and Management Research · doi:10.2991/978-94-6463-433-4_40 · Cited by 11
MirrorFair: Fixing Fairness Bugs in Machine Learning Software via Counterfactual Predictions
Xiao, Y., Zhang, J. M., Liu, Y., Mousavi, M. R., Liu, S., & Xue, D. (2024) · Proceedings of the ACM on software engineering. · doi:10.1145/3660801 · Cited by 14
“Our selection includes ten bias mitigation methods integrated into the AIF 360 toolbox [8], as well as five advanced methods [16, 17, 19, 48, 55] proposed in software engineering.”
Mitigating Subgroup Unfairness in Machine Learning Classifiers: A Data-Driven Approach
Yin, L., Gupta, S., & Jagadish, H. V. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00171 · Cited by 13
Testing Correctness, Fairness, and Robustness of Speech Emotion Recognition Models
Derington, A., Wierstorf, H., Özkil, A. G., Eyben, F., Burkhardt, F., & Schuller, B. W. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3547218 · Cited by 10
Fairness Testing Through Extreme Value Theory
Monjezi, V., Trivedi, A., Крейнович, В., & Tizpaz-Niari, S. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00070 · Cited by 12
“For evaluating fairness in average-based scenarios, in addition to AOD and EOD metrics, we also included Statistical Parity Difference (SPD), and Disparate Impact (DI) which compare the probabilities of favorable outcomes among protected groups [54].”
Making ML Models Fairer Through Explanations: The Case of LimeOut
Alves, G., Bhargava, V., Couceiro, M., & Napoli, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72610-2_1 · Cited by 11
Administrative Justice in a Digital World: Challenges and Solutions
Henman, P. W. F. (2021) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780190903084.013.23 · Cited by 10
Trustworthy Fairness Metric Applied to AI-Based Decisions in Food-Energy-Water
Uslu, S., Kaur, D., Rivera, S. J., Durresi, A., Durrësi, M., & Babbar‐Sebens, M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-99587-4_37 · Cited by 10
Assembled Bias: Beyond Transparent Algorithmic Bias
Waller, R. L., & Waller, R. L. (2022) · Minds and Machines · doi:10.1007/s11023-022-09605-x · Cited by 12
Hirzel, M. J., Kate, K., Ram, P., Shinnar, A., & Tsay, J. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3542630 · Cited by 8
Hort, M., & Sarro, F. (2022) · doi:10.1145/3524491.3527308 · Cited by 11
Assessing the Impact of Cognitive Biases in AI Project Development
Bernault, C., Juan, S., Delmas, A., André, J., Rodier, M., & Kaadoud, I. C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35891-3_24 · Cited by 11
Sun, L., Li, Z., Zhou, Z., Lou, S., Li, W., & Zhang, Y. (2023) · Artificial intelligence for engineering design analysis and manufacturing · doi:10.1017/s0890060422000270 · Cited by 10
“, 2018) and the AI fairness 360 toolkit (Bellamy et al., 2019) guide design practitioners to assess and mitigate potential unfairness caused by AI during ideation.”
BackgroundSelf-citationDemocratizing Quality-Based Machine Learning Development through Extended Feature Models
d’Aloisio, G., Marco, A. D., & Stilo, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30826-0_5 · Cited by 11
Fairness in Forecasting of Observations of Linear Dynamical Systems
Zhou, Q., Mareček, J., & Shorten, R. N. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14050 · Cited by 10
Zhu, J., Gu, L., Wu, X., Li, Z., Harada, T., & Zhu, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26712 · Cited by 10
Austin, T., & Rawal, B. S. (2023) · Algorithms · doi:10.3390/a16080363 · Cited by 11
Statistical Methods for Assessing Differences in False Non-match Rates Across Demographic Groups
Schuckers, M. E., Purnapatra, S., Fatima, K., Hou, D., & Schuckers, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-37731-0_41 · Cited by 8
“In other artificial intelligence (AI) research, evaluation metrics include demographic parity, equalized odds, and equal opportunity [7] [8] [9] [10].”
BackgroundFEAMOE: Fair, Explainable and Adaptive Mixture of Experts
Sharma, S. K., Henderson, J., & Ghosh, J. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/55 · Cited by 11
Trust, Privacy and Security Aspects of Bias and Fairness in Machine Learning
Atabek, A., Eralp, E., & Gürsoy, M. E. (2023) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa58951.2023.00023 · Cited by 8
“In this paper, we use the implementation of SEDF in IBM AIF360 [9], [10], which follows the SEDF formulation by Foulds et al. [8].”
MethodFairness in Large Language Models in Three Hours
Doan, T. V., Wang, Z., Hoang, N., & Zhang, W. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679090 · Cited by 15
“First, we present three essential tools: Perspective API [23], developed by Google Jigsaw, detects toxicity in text; AI Fairness 360 (AIF360) [3], an open-source toolkit with various algorithms and tools; and Aequitas [39], another open-source toolkit, audits fairness and bias in LLMs, aiding data…”
MethodMultimodal Review Generation with Privacy and Fairness Awareness
Vu, X.-S., Nguyen, T.-S., Le, D.-T., & Jiang, L. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.37 · Cited by 13
DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces
Friedrich, N., Lauscher, A., Ponzetto, S. P., & Glavaš, G. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-demos.11 · Cited by 9
Detection and Mitigation of Rare Subclasses in Deep Neural Network Classifiers
Paterson, C., Călinescu, R., & Picardi, C. (2021) · IEEE International Conference on Artificial Intelligence Testing (AITest) · doi:10.1109/aitest52744.2021.00012 · Cited by 12
Don’t Throw it Away! The Utility of Unlabeled Data in Fair Decision Making
Rateike, M., Majumdar, A., Mineeva, O., Gummadi, K. P., & Valera, I. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533199 · Cited by 23
Fairness Certification for Natural Language Processing and Large Language Models
Freiberger, V., & Buchmann, E. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66329-1_39 · Cited by 13
Evidence-based explanation to promote fairness in AI systemsPreprint
Ferreira, J. J., & Monteiro, M. D. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01525 · Cited by 9
The Impact of Presentation Style on Human-In-The-Loop Detection of Algorithmic BiasPreprint
Law, P.-M., Malik, S., Du, F., & Sinha, M. (2020) · arXiv (Cornell University) · doi:10.20380/gi2020.30 · Cited by 12
An Empirical Study of Modular Bias Mitigators and EnsemblesPreprint
Feffer, M., Hirzel, M. J., Hoffman, S. C., Kate, K., Ram, P., & Shinnar, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.00751 · Cited by 9
Self-citationSurvey of Trustworthy AI: A Meta Decision of AIPreprint
Wu, C., Lib, Y.-F., & Bouvry, P. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.00380 · Cited by 10
“One of the open-source tools is AI Fairness 360 (AIF360) [84] [84].”
Methodfairret: a Framework for Differentiable Fairness Regularization Terms
Buyl, M., Defrance, M., & Bie, T. D. (2023) · Ghent University Academic Bibliography (Ghent University) · doi:10.48550/arxiv.2310.17256 · Cited by 10
OxonFair: A Flexible Toolkit for Algorithmic FairnessPreprint
Delaney, E. D., Fu, Z., Wachter, S., Mittelstadt, B., & Russell, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4894794 · Cited by 9
Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and EthicsPreprint
Khan, A., Khan, M. Z., Zainab, A., Jamshed, S., Ahmad, S., Khatib, K., Bibi, F., & Rehman, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.12365 · Cited by 14
FairUDT: Fairness-aware Uplift Decision Trees
Zahid, A., Ali, A. R., Raza, S., Shahnawaz, R., Kamiran, F., & Karim, A. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113068 · Cited by 8
Gulamali, F. F., Sawant, A. S., Liharska, L. E., Horowitz, C. R., Chan, L., Hofer, I. S., Singh, K., Richardson, L. D., Mensah, E., Charney, A. W., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/71757 · Cited by 7
“Attempts to mitigate bias have focused on fairness metric–based algorithm optimization after training on the data [2,6,9].”
Fahmy, A. M. (2025) · Premier journal of public health. · doi:10.70389/pjph.100021 · Cited by 9
Biswas, I. (2025) · Journal of Medical Ethics · doi:10.1136/jme-2025-110913 · Cited by 7
RetractedBenitez-Aurioles, J., Joules, A., Brusini, I., Peek, N. B., & Sperrin, M. (2026) · Epidemiology · doi:10.1097/ede.0000000000001949 · Cited by 8
Artificial intelligence in emergency medicine: a narrative review
Rego, A., Arango-Ibañez, J. P., Taylor, R. A., Smith, M. E., Jones, D. D., Pelletier, J., Colletti, J. E., Gottlieb, M. A., & Long, B. (2026) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2026.01.028 · Cited by 8
Surrogate Ground Truth Generation to Enhance Binary Fairness Evaluation in Uplift Modeling
Michalsky, F., & Kadıoğlu, S. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00264 · Cited by 10
Biu, P. W., Oliha, J. S., & Obi, O. C. (2024) · Engineering Science & Technology Journal · doi:10.51594/estj.v5i2.826 · Cited by 11
Fairness in Healthcare: Assessing Data Bias and Algorithmic Fairness
Dehghani, F., Malik, N., Lin, J., Bayat, S., & Bento, M. (2024) · International Symposium on Medical Information Processing and Analysis (SIPAIM) · doi:10.1109/sipaim62974.2024.10783630 · Cited by 13
“IBM’s AIF360 open-source toolkit is utilized to conduct all experiments for bias detection [6], as it provides various state-of-the-art fairness evaluation metrics.”
Impact on bias mitigation algorithms to variations in inferred sensitive attribute uncertainty
Wang, Y., & Singh, L. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1520330 · Cited by 9
Lee, Y., Chang, C., & Yang, C. C. (2025) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-025-00194-9 · Cited by 10
“Using automated bias detection tools, such as IBM’s AI Fairness 360 [36], can also be effective but it is mandatory to involve human annotators with cultural expertise to catch subtle cues.”
From Expectation to Habit: Why do Software Practitioners Adopt Fairness Toolkits?
Voria, G., Lambiase, S., Schiavone, M. C., Catolino, G., & Palomba, F. (2025) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Society (ICSE-SEIS) · doi:10.1109/icse-seis66351.2025.00015 · Cited by 8
“AIF360 [16], developed by IBM, offers a comprehensive suite of fairness metrics and bias mitigation techniques.”
Sayyadnejad, M. M., Asgari, A., Sami, A., & Tahayori, H. (2025) · Empirical Software Engineering · doi:10.1007/s10664-025-10710-5 · Cited by 8
Li, P. L., Chai, X., Campbell, F., Liao, J., Abburu, N., Kang, M., Niculescu, I., Brake, G., Patil, S., Dooley, J., et al. (2021) · IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip52600.2021.00026 · Cited by 9
Creating Unbiased Machine Learning Models by Design
Breeden, J. L., & Leonova, E. (2021) · Journal of risk and financial management · doi:10.3390/jrfm14110565 · Cited by 7
Can Ensembling Preprocessing Algorithms Lead to Better Machine Learning Fairness?
Badran, K., Côté, P.-O., Kolopanis, A., Bouchoucha, R., Collante, A., Costa, D. E., Shihab, E., & Khomh, F. (2023) · Computer · doi:10.1109/mc.2022.3220707 · Cited by 7
Lambers, L., & Uchitel, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30826-0 · Cited by 7
When Fair Classification Meets Noisy Protected Attributes
Ghosh, A., Kvitca, P., & Wilson, C. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604707 · Cited by 18
Age Bias: A Tremendous Challenge for Algorithms in the Job Candidate Screening Process
Harris, C. G. (2022) · IEEE International Symposium on Technology and Society (ISTAS) · doi:10.1109/istas55053.2022.10227135 · Cited by 9
“Table 3 illustrates how each of the selected methods can reduce, but not eliminate this bias (for a better explanation of each of these fairness metrics, see [42] and [44]).”
BackgroundToward Fairness Across Skin Tones in Dermatological Image Processing
Almuzaini, A. A., Dendukuri, S. K., & Singh, V. K. (2023) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr59079.2023.00030 · Cited by 10
“…building fairness-centric adversarial networks [2], reweighing multimodal features [3], reweighing and combining multiple model outputs [4], or creating new mid-level representations that maintain high prediction accuracy but minimize the correlation with sensitive/demographic attributes [6].”
BackgroundFair Transition Loss: From label noise robustness to bias mitigation
Canalli, Y., Braida, F., Alvim, L. G. M., & Zimbrão, G. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111711 · Cited by 9
Seth, P., & Pai, A. K. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00067 · Cited by 11
Adapting Fairness Interventions to Missing Values
Feng, R., Calmon, F. P., & Wang, H. (2023) · neural information processing systems · doi:10.52202/075280-2595 · Cited by 20
Zhang, Y., Bellamy, R., Singh, M., & Liao, Q. V. (2020) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3334480.3375059 · Cited by 7
Self-citationDiversity Blocks for De-biasing Classification Models
Nagpal, S., Singh, M., Singh, R., & Vatsa, M. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304931 · Cited by 8
Self-citationAttenuation of Human Bias in Artificial Intelligence: An Exploratory Approach
Ahmed, S., Athyaab, S. A., & Muqtadeer, S. A. (2021) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict50816.2021.9358507 · Cited by 10
“To accomplish this task, we have some so-called metrics which are defined by IBM’s AIF360 framework [1] which helps developers deal with.”
MethodA Maximal Correlation Framework for Fair Machine Learning
Lee, J. A., Bu, Y., Sattigeri, P., Panda, R., Wornell, G. W., Karlinsky, L., & Feris, R. (2022) · Entropy · doi:10.3390/e24040461 · Cited by 11
Self-citationTrusted Artificial Intelligence: Technique Requirements and Best Practices
Zhang, T., Qin, Y., & Li, Q. (2021) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom53373.2021.00207 · Cited by 8
Locality of Technical Objects and the Role of Structural Interventions for Systemic Change
Cortés, E. C., Rajtmajer, S. M., & Ghosh, D. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3534646 · Cited by 9
Exploring Ethical Requirements Elicitation for Applications in the Context of AI
de Cerqueira, J. A. S., & Canedo, E. D. (2022) · Anais do Simpósio Brasileiro de Sistemas de Informação (SBSI) · doi:10.5753/sbsi_estendido.2022.222269 · Cited by 9
FairLib: A Unified Framework for Assessing and Improving Fairness
Han, X., Shen, A., Li, Y., Frermann, L., Baldwin, T., & Cohn, T. (2022) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2022.emnlp-demos.7 · Cited by 20
Forward Composition Propagation for Explainable Neural Reasoning
Grau, I., Nápoles, G., Bello, M., Salgueiro, Y., & Jastrzębska, A. (2024) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2023.3327834 · Cited by 7
Finding Pareto trade-offs in fair and accurate detection of toxic speech
Gupta, S. S., Kovatchev, V., Das, A., De‐Arteaga, M., & Lease, M. (2025) · Information Research · doi:10.47989/ir30iconf47572 · Cited by 7
FairCORELS, an Open-Source Library for Learning Fair Rule Lists
Aïvodji, U., Ferry, J., Gambs, S., Huguet, M., & Siala, M. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3481965 · Cited by 15
“Existing fairness-enhancing techniques can be categorized into three main families, mitigating biases at different stages of the machine learning pipeline: pre-processing, post-processing and algorithmic modification techniques [6, 13].”
BackgroundDetection and Mitigation of Bias in Ted Talk RatingsPreprint
Acharyya, R., Das, S., Chattoraj, A., Sengupta, O., & Tanveer, M. I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00683 · Cited by 7
Lee, M. S. A., Floridi, L., & Singh, J. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3679975 · Cited by 10
Kobayashi, K., & Nakao, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13494 · Cited by 10
Chen, Y., Wang, J., & Liu, Y. (2020) · arXiv (Cornell University) · Cited by 9
Know Your Model (KYM): Increasing Trust in AI and Machine LearningPreprint
Roszel, M., Norvill, R., Hilger, J., & State, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.11036 · Cited by 9
Deep AUC Maximization for Medical Image Classification: Challenges and OpportunitiesPreprint
Yang, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02400 · Cited by 8
Fairness through Social Welfare OptimizationPreprint
Chen, V. X., & Hooker, J. N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00311 · Cited by 7
Mitigating Bias in Algorithmic Systems -- A Fish-Eye ViewPreprint
Orphanou, K., Otterbacher, J., Kleanthous, S., Batsuren, K., Giunchiglia, F., Bogina, V., Tal, A. S., AlanHartman, & Kuflik, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16953 · Cited by 9
Zanna, K., & Sano, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.08230 · Cited by 8
“For all fairness analyses in our experiments, we utilize a fairness toolkit developed by IBM - AI Fairness 360 (Bellamy et al. [2019]).”
Method
Metadata
- Authors
- Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilović, A., Nagar, S., Ramamurthy, K. N., Richards, J., Saha, D., Sattigeri, P., Singh, M., Varshney, K. R., & Zhang, Y.
- ORCID
- Venue
- IBM Journal of Research and Development
- Publisher
- IBM
- Published
- 2019-07-01
- Volume
- 63
- Issue
- 4/5
- Pages
- 4:1-4:15
- ISSN
- 0018-8646 (ISSN-L)
- OpenAlex
- W2974817986
- Cited by
- 884
- References
- 31
- Citations by year
- 2026: 163 · 2025: 226 · 2024: 145 · 2023: 143 · 2022: 99 · 2021: 69 · 2020: 35 · 2019: 4
- FWCI
- 90.90
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IBM Journal of Research and Development (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
- Keywords
- algorithmic fairness, algorithmic bias detection, bias mitigation, fairness metrics, open-source software toolkit, high-stakes decision making
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.