mlsanityData to 14 Oct 2026

Social Biases in NLP Models as Barriers for Persons with Disabilities

arXiv 2005.00813 ↗First posted 2 May 2020cs.CL cs.AI cs.LGcited by 182

Not on the map. Why?

Abstract (arXiv)

Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social biases from the data on which they are trained. In this paper, we present evidence of such undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis. Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability. We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases; for instance, gun violence, homelessness, and drug addiction are over-represented in texts discussing mental illness.

Key facts. Cited by 182 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 31; 2023: 55; 2024: 37; 2025: 20; 2026: 11.

182 papers.

Sort:

By area:

  1. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  2. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  3. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 897
  4. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  5. 2023StarCoder: may the source be with you!cited by 799
  6. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  7. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  8. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  9. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 441
  10. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  11. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  12. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 349
38 more
  1. 2021Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotationscited by 314
  2. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
  3. 2023Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Modelscited by 192
  4. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  5. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 173
  6. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 155
  7. 2024Investigating Cultural Alignment of Large Language Modelscited by 143
  8. 2022Training Data Influence Analysis and Estimation: A Surveycited by 135
  9. 2023Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendationcited by 114
  10. 2021Re-imagining Algorithmic Fairness in India and Beyondcited by 104
  11. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 98
  12. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
  13. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  14. 2021On Measures of Biases and Harms in NLPcited by 81
  15. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 80
  16. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 75
  17. 2025AgentRxiv: Towards Collaborative Autonomous Researchcited by 72
  18. 2024Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypescited by 59
  19. 2022Re-contextualizing Fairness in NLP: The Case of Indiacited by 55
  20. 2023ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishingcited by 52
  21. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 52
  22. 2021Changing the World by Changing the Datacited by 51
  23. 2023Nationality Bias in Text Generationcited by 50
  24. 2024Robustifying Safety-Aligned Large Language Models through Clean Data Curationcited by 44
  25. 2023Opportunities and Risks of LLMs for Scalable Deliberation with Poliscited by 42
  26. 2025FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steeringcited by 40
  27. 2021Your fairness may vary: Pretrained language model fairness in toxic text classificationcited by 39
  28. 2023Comparing Biases and the Impact of Multilingual Training across Multiple Languagescited by 36
  29. 2023Lost in Translation: Large Language Models in Non-English Content Analysiscited by 35
  30. 2024Gender Bias in Large Language Models across Multiple Languagescited by 35
  31. 2022Data Governance in the Age of Large-Scale Data-Driven Language Technologycited by 33
  32. 2023Quantifying the Dialect Gap and its Correlates Across Languagescited by 33
  33. 2021Detecting Cross-Geographic Biases in Toxicity Modeling on Social Mediacited by 31
  34. 2023On Evaluating and Mitigating Gender Biases in Multilingual Settingscited by 31
  35. 2024Measuring and Reducing LLM Hallucination without Gold-Standard Answerscited by 31
  36. 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
  37. 2023On the Independence of Association Bias and Empirical Fairness in Language Modelscited by 29
  38. 2022Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparitiescited by 28

50 most cited of 182 All 182 (JSON)