mlsanityData to 7 Oct 2026

On the Interplay between Fairness and Explainability

arXiv 2310.16607 ↗First posted 25 Oct 2023cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

In order to build reliable and trustworthy NLP applications, models need to be both fair across different demographics and explainable. Usually these two objectives, fairness and explainability, are optimized and/or examined independently of each other. Instead, we argue that forthcoming, trustworthy NLP systems should consider both. In this work, we perform a first study to understand how they influence each other: do fair(er) models rely on more plausible rationales? and vice versa. To this end, we conduct experiments on two English multi-class text classification datasets, BIOS and ECtHR, that provide information on gender and nationality, respectively, as well as human-annotated rationales. We fine-tune pre-trained language models with several methods for (i) bias mitigation, which aims to improve fairness; (ii) rationale extraction, which aims to produce plausible explanations. We find that bias mitigation algorithms do not always lead to fairer models. Moreover, we discover that empirical fairness and explainability are orthogonal.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 41 of its 60 references that are in the map. First posted on arXiv 25 Oct 2023.

Builds on

41 of 60 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  7. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 996
  8. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  9. 2020Quantifying Attention Flow in Transformerscited by 759
  10. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  11. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  12. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
29 more
  1. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 403
  2. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  3. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  4. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 302
  5. 2016Rationalizing Neural Predictionscited by 281
  6. 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 262
  7. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  8. 2019End-to-End Bias Mitigation by Modelling Biases in Corporacited by 127
  9. 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 102
  10. 2022XAI for Transformers: Better Explanations through Conservative Propagationcited by 100
  11. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
  12. 2021Competency Problems: On Finding and Removing Artifacts in Language Datacited by 91
  13. 2022Interpreting Language Models with Contrastive Explanationscited by 91
  14. 2021Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Casescited by 77
  15. 2019AllenNLP Interpret: A Framework for Explaining Predictions of NLP Modelscited by 74
  16. 2018Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMscited by 67
  17. 2017A causal framework for explaining the predictions of black-box sequence-to-sequence modelscited by 58
  18. 2022FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processingcited by 48
  19. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  20. 2019A Game Theoretic Approach to Class-wise Selective Rationalizationcited by 32
  21. 2022Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifoldcited by 29
  22. 2023On the Independence of Association Bias and Empirical Fairness in Language Modelscited by 29
  23. 2022Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Settingcited by 23
  24. 2022BLIND: Bias Removal With No Demographicscited by 22
  25. 2022Challenges in Applying Explainability Methods to Improve the Fairness of NLP Modelscited by 20
  26. 2022Controlling Bias Exposure for Fair Interpretable Predictionscited by 18
  27. 2023Being Right for Whose Right Reasons?cited by 12
  28. 2023Rather a Nurse than a Physician -- Contrastive Explanations under Investigationcited by 11
  29. 2022Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wildcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 1.

7 papers.

  1. 2025Explainability in Practice: A Survey of Explainable NLP Across Various Domainscited by 11
  2. 2025Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Taskscited by 7
  3. 2025Summarizing Speech: A Comprehensive Surveycited by 5
  4. 2025Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methodscited by 3
  5. 2025Controllable Pareto Trade-off between Fairness and Accuracycited by 0
  6. 2025On the Interplay between Human Label Variation and Model Fairnesscited by 0
  7. 2026From Interpretability to Control: Insights from Six Years of the TrustNLP Workshopcited by 0