mlsanityData to 7 Oct 2026

Balancing out Bias: Achieving Fairness Through Balanced Training

arXiv 2109.08253 ↗First posted 16 Sep 2021cs.CLcited by 34

Not on the map. Why?

Abstract (arXiv)

Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been shown to be effective at mitigating bias, however existing approaches do not directly account for correlations between author demographics and linguistic variables, limiting their effectiveness. To achieve Equal Opportunity fairness, such as equal job opportunity without regard to demographics, this paper introduces a simple, but highly effective, objective for countering bias using balanced training. We extend the method in the form of a gated model, which incorporates protected attributes as input, and show that it is effective at reducing bias in predictions through demographic input perturbation, outperforming all other bias mitigation techniques when combined with balanced training.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

25 of 50 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  6. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  7. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  8. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  9. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  10. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  11. 2016Domain Separation Networkscited by 317
  12. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
13 more
  1. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  2. 2018Gender Bias in Neural Natural Language Processingcited by 210
  3. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 194
  4. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 166
  5. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  6. 2017Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasmcited by 117
  7. 2019Getting Gender Right in Neural Machine Translationcited by 98
  8. 2020Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problemcited by 86
  9. 2019Conditional Learning of Fair Representationscited by 78
  10. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  11. 2021Diverse Adversaries for Mitigating Bias in Trainingcited by 48
  12. 2020Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizationscited by 40
  13. 2018What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Trainingcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 11; 2025: 8; 2026: 4.

34 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 97
  3. 2023A Survey on Fairness in Large Language Modelscited by 91
  4. 2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 66
  5. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  6. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  7. 2022BLIND: Bias Removal With No Demographicscited by 22
  8. 2022Interpreting Unfairness in Graph Neural Networks via Training Node Attributioncited by 18
  9. 2025Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editingcited by 14
  10. 2023Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLPcited by 11
  11. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
  12. 2024Potential and Challenges of Model Editing for Social Debiasingcited by 10
22 more
  1. 2024Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarioscited by 10
  2. 2024An Active Learning Framework for Inclusive Generation by Large Language Modelscited by 5
  3. 2023Fair Text Classification with Wasserstein Independencecited by 4
  4. 2023A Group Fairness Lens for Large Language Modelscited by 4
  5. 2024Addressing Both Statistical and Causal Gender Fairness in NLP Modelscited by 4
  6. 2025Fair Text Classification via Transferable Representationscited by 3
  7. 2023Boosting Fair Classifier Generalization through Adaptive Priority Reweighingcited by 1
  8. 2024A Note on Bias to Completecited by 1
  9. 2025CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognitioncited by 1
  10. 2026Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMscited by 1
  11. 2024HateDebias: On the Diversity and Variability of Hate Speech Debiasingcited by 0
  12. 2024Balancing the Scales: Reinforcement Learning for Fair Classificationcited by 0
  13. 2024Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Modelscited by 0
  14. 2024MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledgecited by 0
  15. 2025FairFlow: Mitigating Dataset Biases through Undecided Learningcited by 0
  16. 2025Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processingcited by 0
  17. 2025Fair-GPTQ: Bias-Aware Quantization for Large Language Modelscited by 0
  18. 2025Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysiscited by 0
  19. 2025Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluationcited by 0
  20. 2026FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistantscited by 0
  21. 2026LLM Nepotism in Organizational Governancecited by 0
  22. 2026Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Datasetcited by 0