mlsanityData to 7 Oct 2026

Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification

arXiv 2106.10826 ↗First posted 21 Jun 2021cs.CL cs.CYcited by 20

Not on the map. Why?

Abstract (arXiv)

Existing bias mitigation methods to reduce disparities in model outcomes across cohorts have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training. Separately, certified word substitution robustness methods have been developed to decrease the impact of spurious features and synonym substitutions on model predictions. While their end goals are different, they both aim to encourage models to make the same prediction for certain changes in the input. In this paper, we investigate the utility of certified word substitution robustness methods to improve equality of odds and equality of opportunity on multiple text classification tasks. We observe that certified robustness methods improve fairness, and using both robustness and bias mitigation methods in training results in an improvement in both fronts

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

38 of 52 references.

References · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  7. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  8. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  9. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  10. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  11. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  12. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 467
26 more
  1. 2018Generating Natural Language Adversarial Examplescited by 422
  2. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  3. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
  4. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  5. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  6. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  7. 2018Adversarial Logit Pairingcited by 224
  8. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  9. 2020Towards Debiasing Sentence Representationscited by 170
  10. 2018Learning Gender-Neutral Word Embeddingscited by 169
  11. 2019Certified Robustness to Adversarial Word Substitutionscited by 164
  12. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  13. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 150
  14. 2019Assessing Social and Intersectional Biases in Contextualized Word Representationscited by 134
  15. 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
  16. 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 72
  17. 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 55
  18. 2019What's in a Name? Reducing Bias in Bios without Access to Protected Attributescited by 51
  19. 2020Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weightingcited by 41
  20. 2020Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigationcited by 36
  21. 2020On Adversarial Bias and the Robustness of Fair Machine Learningcited by 36
  22. 2020Fairness and Robustness in Invariant Learning: A Case Study in Toxicity Classificationcited by 32
  23. 2020Mitigating Gender Bias Amplification in Distribution by Posterior Regularizationcited by 27
  24. 2018A Re-ranker Scheme for Integrating Large Scale NLU modelscited by 9
  25. 2020LOGAN: Local Group Bias Detection by Clusteringcited by 9
  26. 2019Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notescited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 10; 2023: 5; 2024: 2; 2025: 2.

20 papers.

Sort:

  1. 2023A Survey on Fairness in Large Language Modelscited by 91
  2. 2021NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentationcited by 72
  3. 2022Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparitiescited by 27
  4. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  5. 2022Challenges in Applying Explainability Methods to Improve the Fairness of NLP Modelscited by 20
  6. 2022Conditional Supervised Contrastive Learning for Fair Text Classificationcited by 11
  7. 2022Fairness and robustness in anti-causal predictioncited by 10
  8. 2025Robustness and Cybersecurity in the EU Artificial Intelligence Actcited by 10
  9. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  10. 2023Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairnesscited by 7
  11. 2022Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendationcited by 6
  12. 2022Measuring Fairness of Text Classifiers via Prediction Sensitivitycited by 5
8 more
  1. 2022Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classificationcited by 5
  2. 2023Are fairness metric scores enough to assess discrimination biases in machine learning?cited by 3
  3. 2022Sibylvariant Transformations for Robust Text Classificationcited by 2
  4. 2024Does Differential Privacy Impact Bias in Pretrained NLP Models?cited by 2
  5. 2024Collapsed Language Models Promote Fairnesscited by 1
  6. 2023Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognitioncited by 0
  7. 2023Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditingcited by 0
  8. 2025Quantifying Misattribution Unfairness in Authorship Attributioncited by 0