mlsanityData to 14 Oct 2026

Bias in Large Language Models: Origin, Evaluation, and Mitigation

arXiv 2411.10915 ↗First posted 16 Nov 2024cs.CL cs.LGcited by 77

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. We categorize biases as intrinsic and extrinsic, analyzing their manifestations in various NLP tasks. The review critically assesses a range of bias evaluation methods, including data-level, model-level, and output-level approaches, providing researchers with a robust toolkit for bias detection. We further explore mitigation strategies, categorizing them into pre-model, intra-model, and post-model techniques, highlighting their effectiveness and limitations. Ethical and legal implications of biased LLMs are discussed, emphasizing potential harms in real-world applications such as healthcare and criminal justice. By synthesizing current knowledge on bias in LLMs, this review contributes to the ongoing effort to develop fair and responsible AI systems. Our work serves as a comprehensive resource for researchers and practitioners working towards understanding, evaluating, and mitigating bias in LLMs, fostering the development of more equitable AI technologies.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). Builds on 105 of its 190 references that are in the map. First posted on arXiv 16 Nov 2024.

Builds on

105 of 190 references.

References · 105

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  7. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  8. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  9. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  10. 2018Datasheets for Datasetscited by 1,386
  11. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  12. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
38 more
  1. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  2. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  3. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  4. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 1,001
  5. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  6. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  7. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  8. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  9. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  10. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  11. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  12. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  13. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  14. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 455
  15. 2018Gender Bias in Coreference Resolutioncited by 442
  16. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  17. 2019On Measuring Social Biases in Sentence Encoderscited by 398
  18. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 380
  19. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
  20. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  21. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  22. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 337
  23. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  24. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  25. 2019Measuring Bias in Contextualized Word Representationscited by 276
  26. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 253
  27. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
  28. 2017End-to-end Neural Coreference Resolutioncited by 241
  29. 2020Large image datasets: A pyrrhic win for computer vision?cited by 237
  30. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  31. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  32. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 224
  33. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 215
  34. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  35. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  36. 2021Societal Biases in Language Generation: Progress and Challengescited by 202
  37. 2016Enhanced LSTM for Natural Language Inferencecited by 200
  38. 2019Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphologycited by 200

50 most cited of 105 All 105 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 45; 2026: 31.

77 papers.

Sort:

By area:

  1. 2025A Study of LLMs' Preferences for Libraries and Programming Languagescited by 20
  2. 2025SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesiscited by 12
  3. 2024Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertaintycited by 11
  4. 2025DAIQ: Auditing Demographic Attribute Inference from Question in LLMscited by 10
  5. 2026AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitorcited by 10
  6. 2026Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairnesscited by 10
  7. 2026Quantifying and Mitigating Self-Preference Bias of LLM Judgescited by 10
  8. 2025From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMscited by 9
  9. 2025Beyond Nash Equilibrium: Bounded Rationality of LLMs and humans in Strategic Decision-makingcited by 9
  10. 2025FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypescited by 9
  11. 2025Diversity-Enhanced Reasoning for Subjective Questionscited by 9
  12. 2025SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenderscited by 8
38 more
  1. 2025Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensionscited by 7
  2. 2025Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMscited by 7
  3. 2025BiasFilter: An Inference-Time Debiasing Framework for Large Language Modelscited by 6
  4. 2025Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealingcited by 5
  5. 2025Codifying Character Logic in Role-Playingcited by 5
  6. 2025CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMscited by 5
  7. 2025Online-PVLM: Advancing Personalized VLMs with Online Concept Learningcited by 5
  8. 2025Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Taskcited by 4
  9. 2025AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMscited by 4
  10. 2025Simulating a Bias Mitigation Scenario in Large Language Modelscited by 4
  11. 2026Jacobian Scopes: token-level causal attributions in LLMscited by 4
  12. 2025Veracity Bias and Beyond: Uncovering LLMs' Hidden Beliefs in Problem-Solving Reasoningcited by 3
  13. 2025MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncoveredcited by 3
  14. 2025Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluationscited by 3
  15. 2025Textual interpretation of transient image classifications from large language modelscited by 3
  16. 2026Architecting Trust in Artificial Epistemic Agentscited by 3
  17. 2025Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMscited by 2
  18. 2025Analysis of LLM Bias (Chinese Propaganda & Anti-US Sentiment) in DeepSeek-R1 vs. ChatGPT o3-mini-highcited by 2
  19. 2025From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Modelscited by 2
  20. 2025"Amazing, They All Lean Left" -- Analyzing the Political Temperaments of Current LLMscited by 2
  21. 2025AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Modelscited by 2
  22. 2025Mitigating Multimodal Hallucinations via Gradient-based Self-Reflectioncited by 2
  23. 2025Efficient Manifold-Constrained Neural ODE for High-Dimensional Datasetscited by 2
  24. 2025A word association network methodology for evaluating implicit biases in LLMs compared to humanscited by 2
  25. 2025Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Userscited by 2
  26. 2026The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safetycited by 2
  27. 2026When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applicationscited by 2
  28. 2026When AI reviews science: Can we trust the referee?cited by 2
  29. 2025From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modelingcited by 1
  30. 2025Measuring Intent Comprehension in LLMscited by 1
  31. 2025S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modelingcited by 1
  32. 2025Adaptive Repetition for Mitigating Position Bias in LLM-Based Rankingcited by 1
  33. 2025BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injectioncited by 1
  34. 2025Bias Mitigation Agent: Optimizing Source Selection for Fair and Balanced Knowledge Retrievalcited by 1
  35. 2026AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditingcited by 1
  36. 2026BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimizationcited by 1
  37. 2026Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agentscited by 1
  38. 2025Matching Game Preferences Through Dialogical Large Language Models: A Perspectivecited by 0

50 most cited of 77 All 77 (JSON)