mlsanityData to 14 Oct 2026

Addressing Both Statistical and Causal Gender Fairness in NLP Models

arXiv 2404.00463 ↗First posted 30 Mar 2024cs.CL cs.CY cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Statistical fairness stipulates equivalent outcomes for every protected group, whereas causal fairness prescribes that a model makes the same prediction for an individual regardless of their protected characteristics. Counterfactual data augmentation (CDA) is effective for reducing bias in NLP models, yet models trained with CDA are often evaluated only on metrics that are closely tied to the causal fairness notion; similarly, sampling-based methods designed to promote statistical fairness are rarely evaluated for causal fairness. In this work, we evaluate both statistical and causal debiasing methods for gender bias in NLP models, and find that while such methods are effective at reducing bias as measured by the targeted metric, they do not necessarily improve results on other bias metrics. We demonstrate that combinations of statistical and causal debiasing techniques are able to reduce bias measured through both types of metrics.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 44 of its 66 references that are in the map. First posted on arXiv 30 Mar 2024.

Builds on

44 of 66 references.

References · 44

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  5. 2017Counterfactual Fairnesscited by 804
  6. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  7. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  8. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  9. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
  10. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 455
  11. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  12. 2019On Measuring Social Biases in Sentence Encoderscited by 398
32 more
  1. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  2. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  3. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  4. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 224
  5. 2018Gender Bias in Neural Natural Language Processingcited by 211
  6. 2017Avoiding Discrimination through Causal Reasoningcited by 194
  7. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 170
  8. 2020Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biasescited by 167
  9. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  10. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 151
  11. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  12. 2020Intrinsic Bias Metrics Do Not Correlate with Application Biascited by 148
  13. 2017Fair Inference On Outcomescited by 144
  14. 2018Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobservedcited by 94
  15. 2020Reevaluating Adversarial Examples in Natural Languagecited by 85
  16. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  17. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  18. 2019Perturbation Sensitivity Analysis to Detect Unintended Model Biasescited by 74
  19. 2018Causal Reasoning for Algorithmic Fairnesscited by 51
  20. 2019What's in a Name? Reducing Bias in Bios without Access to Protected Attributescited by 51
  21. 2021Diverse Adversaries for Mitigating Bias in Trainingcited by 48
  22. 2021Balancing out Bias: Achieving Fairness Through Balanced Trainingcited by 34
  23. 2021Evaluating Debiasing Techniques for Intersectional Biasescited by 30
  24. 2022Choose Your Lenses: Flaws in Gender Bias Evaluationcited by 29
  25. 2023On the Independence of Association Bias and Empirical Fairness in Language Modelscited by 29
  26. 2019Counterfactual Reasoning for Fair Clinical Risk Predictioncited by 28
  27. 2022Optimising Equal Opportunity Fairness in Model Trainingcited by 22
  28. 2022Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairnesscited by 21
  29. 2023The Possibility of Fairness: Revisiting the Impossibility Theorem in Practicecited by 18
  30. 2023DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervisioncited by 6
  31. 2022Fairness for Text Classification Tasks with Identity Information Data Augmentation Methodscited by 4
  32. 2022Counterfactual Multi-Token Fairness in Text Classificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Exploring Accuracy-Fairness Trade-off in Large Language Modelscited by 1
  2. 2025CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognitioncited by 1
  3. 2024Mitigating Extrinsic Gender Bias for Bangla Classification Taskscited by 0
  4. 2026White-Box Sensitivity Auditing with Steering Vectorscited by 0