mlsanityData to 7 Oct 2026

Sociodemographic Bias in Language Models: A Survey and Forward Path

arXiv 2306.08158 ↗First posted 13 Jun 2023cs.CL cs.AI cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a typology that facilitates examining the different aims: types of bias, quantifying bias, and debiasing techniques. We track the evolution of the latter two questions, then identify current trends and their limitations, as well as emerging techniques. To guide future research towards more effective and reliable solutions, and to help authors situate their work within this broad landscape, we conclude with a checklist of open questions.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 171 of its 310 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

171 of 310 references.

References · 171

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  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. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  8. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  9. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  10. 2017Counterfactual Fairnesscited by 802
  11. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  12. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
38 more
  1. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  2. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  3. 2018Gender Bias in Coreference Resolutioncited by 438
  4. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  5. 2019On Measuring Social Biases in Sentence Encoderscited by 397
  6. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
  7. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  8. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  9. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  10. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  11. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 336
  12. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  13. 2019Measurement and Fairnesscited by 299
  14. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  15. 2019Measuring Bias in Contextualized Word Representationscited by 275
  16. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  17. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 251
  18. 2019Evaluating Gender Bias in Machine Translationcited by 247
  19. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  20. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  21. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 222
  22. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  23. 2018Gender Bias in Neural Natural Language Processingcited by 210
  24. 2019Racial Bias in Hate Speech and Abusive Language Detection Datasetscited by 208
  25. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  26. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 194
  27. 2020Extractive Summarization as Text Matchingcited by 189
  28. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  29. 2020Towards Debiasing Sentence Representationscited by 170
  30. 2018Learning Gender-Neutral Word Embeddingscited by 169
  31. 2020Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biasescited by 167
  32. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 160
  33. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  34. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 150
  35. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  36. 2020Intrinsic Bias Metrics Do Not Correlate with Application Biascited by 148
  37. 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddingscited by 146
  38. 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137

50 most cited of 171 All 171 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 12; 2025: 10; 2026: 3.

27 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  3. 2024The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harmcited by 67
  4. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  5. 2024Beemo: Benchmark of Expert-edited Machine-generated Outputscited by 26
  6. 2024Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approachcited by 25
  7. 2025Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalizationcited by 24
  8. 2023Semantic Consistency for Assuring Reliability of Large Language Modelscited by 15
  9. 2024Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responsescited by 15
  10. 2025A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personascited by 8
  11. 2024Fairness in Large Language Models in Three Hourscited by 7
  12. 2024Hey GPT, Can You be More Racist? Analysis from Crowdsourced Attempts to Elicit Biased Content from Generative AIcited by 6
15 more
  1. 2025The World According to LLMs: How Geographic Origin Influences LLMs' Entity Deduction Capabilitiescited by 5
  2. 2024How far can bias go? Tracing bias from pretraining data to alignmentcited by 4
  3. 2025Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanationcited by 4
  4. 2024With a Grain of SALT: Are LLMs Fair Across Social Dimensions?cited by 3
  5. 2024Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statementscited by 3
  6. 2025Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasetscited by 3
  7. 2024When Stereotypes GTG: The Impact of Predictive Text Suggestions on Gender Bias in Human-AI Co-Writingcited by 2
  8. 2025Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languagescited by 2
  9. 2025Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Contextcited by 1
  10. 2025Social Bias in Multilingual Language Models: A Surveycited by 1
  11. 2025Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yetcited by 0
  12. 2025Phare: A Safety Probe for Large Language Modelscited by 0
  13. 2026Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasingcited by 0
  14. 2026ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cuescited by 0
  15. 2026Sociodemographic Biases in Educational Counselling by Large Language Modelscited by 0