mlsanityData to 14 Oct 2026

Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models

arXiv 2206.03945 ↗First posted 8 Jun 2022cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method can help in combating biases is often left unspecified. In this paper, we briefly review trends in explainability and fairness in NLP research, identify the current practices in which explainability methods are applied to detect and mitigate bias, and investigate the barriers preventing XAI methods from being used more widely in tackling fairness issues.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 72 of its 99 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

72 of 99 references.

References · 72

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2020Extracting Training Data from Large Language Modelscited by 2,189
  9. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  10. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  12. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
38 more
  1. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  2. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  3. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  4. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  5. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  6. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  7. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  9. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  10. 2019Attention is not Explanationcited by 929
  11. 2017Counterfactual Fairnesscited by 804
  12. 2019Designing and Interpreting Probes with Control Taskscited by 640
  13. 2019Attention is not not Explanationcited by 636
  14. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  15. 2018Gender Bias in Coreference Resolutioncited by 442
  16. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 407
  17. 2020Fairness in Machine Learning: A Surveycited by 370
  18. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  19. 2020Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Makingcited by 281
  20. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 254
  21. 2019Evaluating Gender Bias in Machine Translationcited by 249
  22. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  23. 2020Information-Theoretic Probing with Minimum Description Lengthcited by 232
  24. 2021Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Modelscited by 222
  25. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 216
  26. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  27. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  28. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 196
  29. 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
  30. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 178
  31. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 151
  32. 2020Intrinsic Bias Metrics Do Not Correlate with Application Biascited by 148
  33. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  34. 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137
  35. 2020CausaLM: Causal Model Explanation Through Counterfactual Language Modelscited by 117
  36. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 106
  37. 2019Attention in Natural Language Processingcited by 101
  38. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 7; 2024: 4; 2025: 3; 2026: 4.

20 papers.

Sort:

By area:

  1. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 25
  2. 2023A Critical Survey on Fairness Benefits of Explainable AIcited by 16
  3. 2023Being Right for Whose Right Reasons?cited by 12
  4. 2022XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Modelscited by 8
  5. 2023On the Interplay between Fairness and Explainabilitycited by 7
  6. 2022Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Informationcited by 6
  7. 2023Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editorscited by 6
  8. 2023Towards Conceptualization of "Fair Explanation": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderatorscited by 6
  9. 2024Procedural Fairness in Machine Learningcited by 4
  10. 2025B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainabilitycited by 4
  11. 2023Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifierscited by 3
  12. 2025Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methodscited by 3
8 more
  1. 2026LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactualscited by 2
  2. 2024Mapping the Potential of Explainable AI for Fairness Along the AI Lifecyclecited by 1
  3. 2026Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Modelscited by 1
  4. 2023Beyond XAI:Obstacles Towards Responsible AIcited by 0
  5. 2024MAPX: An explainable model-agnostic framework for the detection of false information on social media networkscited by 0
  6. 2025Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?cited by 0
  7. 2026From Interpretability to Control: Insights from Six Years of the TrustNLP Workshopcited by 0
  8. 2026SCM-based Fairness and Faithful Explainability for Legal Document Classificationcited by 0