mlsanityData to 7 Oct 2026

Generative Language Models Exhibit Social Identity Biases

arXiv 2310.15819 ↗First posted 24 Oct 2023cs.CL cs.CYcited by 107

Not on the map. Why?

Abstract (arXiv)

The surge in popularity of large language models has given rise to concerns about biases that these models could learn from humans. We investigate whether ingroup solidarity and outgroup hostility, fundamental social identity biases known from social psychology, are present in 56 large language models. We find that almost all foundational language models and some instruction fine-tuned models exhibit clear ingroup-positive and outgroup-negative associations when prompted to complete sentences (e.g., "We are..."). Our findings suggest that modern language models exhibit fundamental social identity biases to a similar degree as humans, both in the lab and in real-world conversations with LLMs, and that curating training data and instruction fine-tuning can mitigate such biases. Our results have practical implications for creating less biased large-language models and further underscore the need for more research into user interactions with LLMs to prevent potential bias reinforcement in humans.

Key facts. Cited by 107 papers in the map (data through 7 Oct 2026). Builds on 44 of its 113 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

44 of 113 references.

References · 44

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2020Scaling Laws for Neural Language Modelscited by 6,411
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  9. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  11. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  12. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
32 more
  1. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  2. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  3. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  4. 2023PaLM 2 Technical Reportcited by 1,154
  5. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  6. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  7. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  8. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  9. 2023Whose Opinions Do Language Models Reflect?cited by 759
  10. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  11. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  12. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 449
  13. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  14. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  15. 2022UL2: Unifying Language Learning Paradigmscited by 292
  16. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  17. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 251
  18. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 250
  19. 2022Emergent Analogical Reasoning in Large Language Modelscited by 239
  20. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 235
  21. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 217
  22. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  23. 2021What Will it Take to Fix Benchmarking in Natural Language Understanding?cited by 200
  24. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 145
  25. 2022TimeLMs: Diachronic Language Models from Twittercited by 129
  26. 2023Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Clustercited by 106
  27. 2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
  28. 2020DynaSent: A Dynamic Benchmark for Sentiment Analysiscited by 63
  29. 2022Identifying and Manipulating the Personality Traits of Language Modelscited by 40
  30. 2022CommunityLM: Probing Partisan Worldviews from Language Modelscited by 36
  31. 2023Language Models Trained on Media Diets Can Predict Public Opinioncited by 30
  32. 2023ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Modelscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 55; 2026: 39.

107 papers.

Sort:

By area:

  1. 2024Quantifying the Persona Effect in LLM Simulationscited by 164
  2. 2024Emergent social conventions and collective bias in LLM populationscited by 115
  3. 2024Can LLM be a Personalized Judge?cited by 99
  4. 2024Systematic Biases in LLM Simulations of Debatescited by 98
  5. 2023Do LLM Agents Exhibit Social Behavior?cited by 53
  6. 2025SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviorscited by 48
  7. 2025PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runscited by 33
  8. 2024Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targetscited by 31
  9. 2024Conformity in Large Language Modelscited by 30
  10. 2024A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedianscited by 29
  11. 2025An Evaluation of Cultural Value Alignment in LLMcited by 28
  12. 2025The simulation of judgment in LLMscited by 22
38 more
  1. 2025Group size effects and collective misalignment in LLM multi-agent systemscited by 16
  2. 2025C3AI: Crafting and Evaluating Constitutions for Constitutional AIcited by 13
  3. 2026Evaluating LLMs in Finance Requires Explicit Bias Considerationcited by 11
  4. 2025ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learningcited by 10
  5. 2025Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Mergingcited by 10
  6. 2025Silenced Biases: The Dark Side LLMs Learned to Refusecited by 10
  7. 2024Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoptioncited by 9
  8. 2025FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypescited by 9
  9. 2025AI use in American newspapers is widespread, uneven, and rarely disclosedcited by 9
  10. 2025Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicitycited by 8
  11. 2025Language Models Predict Empathy Gaps Between Social In-groups and Out-groupscited by 6
  12. 2025Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essayscited by 6
  13. 2024I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Modelscited by 5
  14. 2024GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?cited by 5
  15. 2025Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Taskscited by 5
  16. 2025A Review of Incorporating Psychological Theories in LLMscited by 5
  17. 2025AI Agent Behavioral Sciencecited by 5
  18. 2025Political Ideology Shifts in Large Language Modelscited by 5
  19. 2025To Mask or to Mirror: Human-AI Alignment in Collective Reasoningcited by 5
  20. 2026When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agentscited by 5
  21. 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Promptscited by 5
  22. 2024How far can bias go? Tracing bias from pretraining data to alignmentcited by 4
  23. 2025iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to Newscited by 4
  24. 2025Mitigating Gender Bias via Fostering Exploratory Thinking in LLMscited by 4
  25. 2025StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Frameworkcited by 4
  26. 2025Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanationcited by 4
  27. 2025Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shapingcited by 3
  28. 2025How large language models judge and influence human cooperationcited by 3
  29. 2025The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systemscited by 3
  30. 2026Invisible failures in human-AI interactionscited by 3
  31. 2024Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistancecited by 2
  32. 2025Reproducibility Study of "Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents"cited by 2
  33. 2025C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Modelscited by 2
  34. 2025From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Modelscited by 2
  35. 2025Infected Smallville: How Disease Threat Shapes Sociality in LLM Agentscited by 2
  36. 2025Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Modelscited by 2
  37. 2025Extreme Self-Preference in Language Modelscited by 2
  38. 2025Social Simulations with Large Language Model Risk Utopian Illusioncited by 2

50 most cited of 107 All 107 (JSON)