mlsanityData to 7 Oct 2026

Bias and Fairness in Large Language Models: A Survey

arXiv 2309.00770 ↗First posted 2 Sep 2023cs.CL cs.AI cs.CYcited by 626

Not on the map. Why?

Cited by 39 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, perpetuate, and amplify harmful social biases. In this paper, we present a comprehensive survey of bias evaluation and mitigation techniques for LLMs. We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing, defining distinct facets of harm and introducing several desiderata to operationalize fairness for LLMs. We then unify the literature by proposing three intuitive taxonomies, two for bias evaluation, namely metrics and datasets, and one for mitigation. Our first taxonomy of metrics for bias evaluation disambiguates the relationship between metrics and evaluation datasets, and organizes metrics by the different levels at which they operate in a model: embeddings, probabilities, and generated text. Our second taxonomy of datasets for bias evaluation categorizes datasets by their structure as counterfactual inputs or prompts, and identifies the targeted harms and social groups; we also release a consolidation of publicly-available datasets for improved access. Our third taxonomy of techniques for bias mitigation classifies methods by their intervention during pre-processing, in-training, intra-processing, and post-processing, with granular subcategories that elucidate research trends. Finally, we identify open problems and challenges for future work. Synthesizing a wide range of recent research, we aim to provide a clear guide of the existing literature that empowers researchers and practitioners to better understand and prevent the propagation of bias in LLMs.

Key facts. Cited by 626 papers in the map (data through 7 Oct 2026). Builds on 189 of its 256 references that are in the map. First posted on arXiv 2 Sep 2023.

Builds on

189 of 256 references.

References · 189

  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. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  8. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  10. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  11. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  12. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
38 more
  1. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  10. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  11. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  12. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  13. 2018Datasheets for Datasetscited by 1,371
  14. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  15. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  16. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  17. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  18. 2018Model Cards for Model Reportingcited by 1,068
  19. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  20. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  21. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  22. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  23. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  24. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  25. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  26. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  27. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  28. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  29. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  30. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  31. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 481
  32. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  33. 2021Dynabench: Rethinking Benchmarking in NLPcited by 447
  34. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  35. 2018Gender Bias in Coreference Resolutioncited by 438
  36. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  37. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  38. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 410

50 most cited of 189 All 189 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 215; 2025: 250; 2026: 146.

626 papers.

Sort:

By area:

  1. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  2. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  3. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 292
  4. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 277
  5. 2024Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judgecited by 249
  6. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  7. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
  8. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  9. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  10. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  11. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  12. 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 117
38 more
  1. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 117
  2. 2024Emergent social conventions and collective bias in LLM populationscited by 115
  3. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 114
  4. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 100
  5. 2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 97
  6. 2024ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teamingcited by 96
  7. 2024Large Language Models are Geographically Biasedcited by 91
  8. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 89
  9. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  10. 2024Towards Conversational Diagnostic AIcited by 79
  11. 2024Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationcited by 79
  12. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  13. 2025LLM Generated Persona is a Promise with a Catchcited by 77
  14. 2025JudgeLRM: Large Reasoning Models as a Judgecited by 76
  15. 2024Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluationcited by 73
  16. 2024The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harmcited by 67
  17. 2025Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinionscited by 64
  18. 2024Red Teaming Visual Language Modelscited by 62
  19. 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agentscited by 62
  20. 2024Can Large Language Model Agents Simulate Human Trust Behavior?cited by 62
  21. 2024Building Guardrails for Large Language Modelscited by 61
  22. 2024OpenBias: Open-set Bias Detection in Text-to-Image Generative Modelscited by 61
  23. 2024We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMscited by 61
  24. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  25. 2024A Comprehensive Survey of Foundation Models in Medicinecited by 56
  26. 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
  27. 2024Conformal Prediction for Natural Language Processing: A Surveycited by 52
  28. 2024LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedbackcited by 51
  29. 2024UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Modelscited by 49
  30. 2025A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challengescited by 46
  31. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 45
  32. 2024Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Modelscited by 44
  33. 2025VerIF: Verification Engineering for Reinforcement Learning in Instruction Followingcited by 43
  34. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankerscited by 42
  35. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 42
  36. 2024Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluationcited by 41
  37. 2024CodecLM: Aligning Language Models with Tailored Synthetic Datacited by 39
  38. 2024Anchoring Bias in Large Language Models: An Experimental Studycited by 37

50 most cited of 626 All 626 (JSON)