mlsanityData to 13 Oct 2026

Diverse Adversaries for Mitigating Bias in Training

arXiv 2101.10001 ↗First posted 25 Jan 2021cs.LG cs.AIcited by 48

Not on the map. Why?

Abstract (arXiv)

Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this paper, we propose a novel approach to adversarial learning based on the use of multiple diverse discriminators, whereby discriminators are encouraged to learn orthogonal hidden representations from one another. Experimental results show that our method substantially improves over standard adversarial removal methods, in terms of reducing bias and the stability of training.

Key facts. Cited by 48 papers in the map (data through 13 Oct 2026). Builds on 11 of its 15 references that are in the map. First posted on arXiv 25 Jan 2021.

Builds on

11 of 15 references.

References · 11

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,909
  3. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 451
  4. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 347
  5. 2016Domain Separation Networkscited by 318
  6. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  7. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 196
  8. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 168
  9. 2017Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasmcited by 118
  10. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  11. 2018What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Trainingcited by 17

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 11; 2023: 13; 2024: 11; 2025: 9.

48 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 636
  2. 2023A Survey on Fairness in Large Language Modelscited by 93
  3. 2025FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steeringcited by 39
  4. 2021Balancing out Bias: Achieving Fairness Through Balanced Trainingcited by 34
  5. 2021Contrastive Learning for Fair Representationscited by 34
  6. 2022Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Informationcited by 33
  7. 2022MABEL: Attenuating Gender Bias using Textual Entailment Datacited by 31
  8. 2021Evaluating Debiasing Techniques for Intersectional Biasescited by 30
  9. 2024SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agentscited by 30
  10. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  11. 2023Parameter-efficient Modularised Bias Mitigation via AdapterFusioncited by 25
  12. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
36 more
  1. 2022Optimising Equal Opportunity Fairness in Model Trainingcited by 22
  2. 2022BLIND: Bias Removal With No Demographicscited by 22
  3. 2023Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biasescited by 21
  4. 2021Fairness-aware Class Imbalanced Learningcited by 19
  5. 2022Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworkscited by 18
  6. 2024Large Language Model Bias Mitigation from the Perspective of Knowledge Editingcited by 16
  7. 2023Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuningcited by 15
  8. 2024Identifying and Mitigating Social Bias Knowledge in Language Modelscited by 13
  9. 2024A Chinese Dataset for Evaluating the Safeguards in Large Language Modelscited by 12
  10. 2022Conditional Supervised Contrastive Learning for Fair Text Classificationcited by 11
  11. 2023Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLPcited by 11
  12. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
  13. 2022Fair NLP Models with Differentially Private Text Encoderscited by 9
  14. 2022Towards Equal Opportunity Fairness through Adversarial Learningcited by 8
  15. 2022FairGrad: Fairness Aware Gradient Descentcited by 8
  16. 2023Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptionscited by 8
  17. 2024Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapterscited by 8
  18. 2023DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervisioncited by 6
  19. 2025Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approachcited by 5
  20. 2022fairlib: A Unified Framework for Assessing and Improving Classification Fairnesscited by 4
  21. 2023Fair Text Classification with Wasserstein Independencecited by 4
  22. 2024Addressing Both Statistical and Causal Gender Fairness in NLP Modelscited by 4
  23. 2022Systematic Evaluation of Predictive Fairnesscited by 3
  24. 2025Fair Text Classification via Transferable Representationscited by 3
  25. 2025EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognitioncited by 3
  26. 2023How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translationcited by 2
  27. 2024Collapsed Language Models Promote Fairnesscited by 1
  28. 2023Transferring Fairness using Multi-Task Learning with Limited Demographic Informationcited by 0
  29. 2024HateDebias: On the Diversity and Variability of Hate Speech Debiasingcited by 0
  30. 2024Balancing the Scales: Reinforcement Learning for Fair Classificationcited by 0
  31. 2024Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Modelscited by 0
  32. 2025Fair Sufficient Representation Learningcited by 0
  33. 2025Deep Fair Learning: Task-Aware Fair Representations via Joint Distance-Covariance Regularizationcited by 0
  34. 2025Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processingcited by 0
  35. 2025Benchmarking Gender and Political Bias in Large Language Modelscited by 0
  36. 2025Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysiscited by 0