mlsanityData to 14 Oct 2026

Persistent Anti-Muslim Bias in Large Language Models

arXiv 2101.05783 ↗First posted 14 Jan 2021cs.CL cs.LGcited by 377

Not on the map. Why?

Cited by 21 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

It has been observed that large-scale language models capture undesirable societal biases, e.g. relating to race and gender; yet religious bias has been relatively unexplored. We demonstrate that GPT-3, a state-of-the-art contextual language model, captures persistent Muslim-violence bias. We probe GPT-3 in various ways, including prompt completion, analogical reasoning, and story generation, to understand this anti-Muslim bias, demonstrating that it appears consistently and creatively in different uses of the model and that it is severe even compared to biases about other religious groups. For instance, "Muslim" is analogized to "terrorist" in 23% of test cases, while "Jewish" is mapped to "money" in 5% of test cases. We quantify the positive distraction needed to overcome this bias with adversarial text prompts, and find that use of the most positive 6 adjectives reduces violent completions for "Muslims" from 66% to 20%, but which is still higher than for other religious groups.

Key facts. Cited by 377 papers in the map (data through 14 Oct 2026). Builds on 14 of its 19 references that are in the map. First posted on arXiv 14 Jan 2021.

Builds on

14 of 19 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2020Reformer: The Efficient Transformercited by 1,668
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  6. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  7. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  8. 2016Self-critical Sequence Training for Image Captioningcited by 547
  9. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  10. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  11. 2018Gender Bias in Neural Natural Language Processingcited by 211
  12. 2015Semi-supervised Sequence Learningcited by 198
2 more
  1. 2019Gradio: Hassle-Free Sharing and Testing of ML Models in the Wildcited by 178
  2. 2019Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Functioncited by 57

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 42; 2023: 112; 2024: 105; 2025: 73; 2026: 29.

377 papers.

Sort:

By area:

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  3. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  4. 2023PaLM 2 Technical Reportcited by 1,162
  5. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  6. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 672
  7. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 656
  8. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  9. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 513
  10. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  11. 2023DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretrainingcited by 399
  12. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 337
38 more
  1. 2023Data Selection for Language Models via Importance Resamplingcited by 329
  2. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 278
  3. 2023Can Large Language Models Transform Computational Social Science?cited by 250
  4. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 249
  5. 2023Pretraining Language Models with Human Preferencescited by 247
  6. 2023Large Language Model Alignment: A Surveycited by 243
  7. 2021Societal Biases in Language Generation: Progress and Challengescited by 202
  8. 2023Knowledge Editing for Large Language Models: A Surveycited by 194
  9. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 191
  10. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  11. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 187
  12. 2023Gender bias and stereotypes in Large Language Modelscited by 187
  13. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 181
  14. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
  15. 2023GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Modelscited by 176
  16. 2021Challenges in Detoxifying Language Modelscited by 169
  17. 2023Personality Traits in Large Language Modelscited by 169
  18. 2023A Categorical Archive of ChatGPT Failurescited by 168
  19. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
  20. 2023Having Beer after Prayer? Measuring Cultural Bias in Large Language Modelscited by 153
  21. 2024Investigating Cultural Alignment of Large Language Modelscited by 143
  22. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 135
  23. 2024Jailbreaking Attack against Multimodal Large Language Modelcited by 135
  24. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 124
  25. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 123
  26. 2023DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Modelscited by 123
  27. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  28. 2023Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Healthcited by 118
  29. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  30. 2024BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practicescited by 114
  31. 2023Generative Language Models Exhibit Social Identity Biasescited by 111
  32. 2024Cognitive Bias in Decision-Making with LLMscited by 106
  33. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  34. 2024ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teamingcited by 98
  35. 2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 98
  36. 2023A Survey on Fairness in Large Language Modelscited by 95
  37. 2024Large Language Models are Geographically Biasedcited by 93
  38. 2023Language Model Behavior: A Comprehensive Surveycited by 92

50 most cited of 377 All 377 (JSON)