mlsanityData to 7 Oct 2026

Nationality Bias in Text Generation

arXiv 2302.02463 ↗First posted 5 Feb 2023cs.CL cs.AIcited by 50

Not on the map. Why?

Abstract (arXiv)

Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore the debiasing method of adversarial triggering. Our results show that GPT-2 demonstrates significant bias against countries with lower internet users, and adversarial triggering effectively reduces the same.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Builds on 15 of its 33 references that are in the map. First posted on arXiv 5 Feb 2023.

Builds on

15 of 33 references.

References · 15

  1. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  2. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  3. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  4. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  5. 2018Gender Bias in Coreference Resolutioncited by 438
  6. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  7. 2019Measuring Bias in Contextualized Word Representationscited by 275
  8. 2020Social Biases in NLP Models as Barriers for Persons with Disabilitiescited by 182
  9. 2019On Measuring and Mitigating Biased Inferences of Word Embeddingscited by 112
  10. 2020Contextualizing Hate Speech Classifiers with Post-hoc Explanationcited by 84
  11. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  12. 2021On Measures of Biases and Harms in NLPcited by 81
3 more
  1. 2019Perturbation Sensitivity Analysis to Detect Unintended Model Biasescited by 74
  2. 2021EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Predictioncited by 17
  3. 2021Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Modelscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 20; 2025: 14; 2026: 3.

50 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  3. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 329
  4. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  5. 2024Investigating Cultural Alignment of Large Language Modelscited by 140
  6. 2024Design Principles for Generative AI Applicationscited by 57
  7. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  8. 2024When Large Language Models Meet Vector Databases: A Surveycited by 39
  9. 2023GPT-who: An Information Density-based Machine-Generated Text Detectorcited by 38
  10. 2023Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Modelscited by 32
  11. 2023Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implicationscited by 29
  12. 2024Navigating LLM Ethics: Advancements, Challenges, and Future Directionscited by 28
38 more
  1. 2024ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Modelscited by 28
  2. 2024'Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participantscited by 27
  3. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  4. 2023Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Modelscited by 20
  5. 2023Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Modelscited by 20
  6. 2024Noisy Neighbors: Efficient membership inference attacks against LLMscited by 20
  7. 2025BiasEdit: Debiasing Stereotyped Language Models via Model Editingcited by 18
  8. 2023Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articlescited by 16
  9. 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
  10. 2024Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Educationcited by 15
  11. 2025Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluationscited by 14
  12. 2025Dissecting Bias in LLMs: A Mechanistic Interpretability Perspectivecited by 14
  13. 2023Towards a Holistic Approach: Understanding Sociodemographic Biases in NLP Models using an Interdisciplinary Lenscited by 9
  14. 2024Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Frameworkcited by 8
  15. 2025Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategiescited by 8
  16. 2024Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunitiescited by 7
  17. 2024Evaluation of Geographical Distortions in Language Modelscited by 6
  18. 2025More of the Same: Persistent Representational Harms Under Increased Representationcited by 6
  19. 2025Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysiscited by 5
  20. 2025LLMs Reproduce Stereotypes of Sexual and Gender Minoritiescited by 4
  21. 2024The Life Cycle of Large Language Models: A Review of Biases in Educationcited by 3
  22. 2025Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Makingcited by 3
  23. 2023Trustworthiness of Children Stories Generated by Large Language Modelscited by 2
  24. 2025Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Modelscited by 2
  25. 2026ProText: A benchmark dataset for measuring (mis)gendering in long-form textscited by 2
  26. 2023Potential Societal Biases of ChatGPT in Higher Education: A Scoping Reviewcited by 1
  27. 2024Race and Privacy in Broadcast Police Communicationscited by 1
  28. 2024Implicit Priors Editing in Stable Diffusion via Targeted Token Adjustmentcited by 1
  29. 2025Social Bias in Multilingual Language Models: A Surveycited by 1
  30. 2023Is a Prestigious Job the same as a Prestigious Country? A Case Study on Multilingual Sentence Embeddings and European Countriescited by 0
  31. 2024ARTiST: Automated Text Simplification for Task Guidance in Augmented Realitycited by 0
  32. 2024Learning to Write Rationally: How Information Is Distributed in Non-Native Speakers' Essayscited by 0
  33. 2025DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Modelscited by 0
  34. 2025How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Languagecited by 0
  35. 2025Measuring Stereotype and Deviation Biases in Large Language Modelscited by 0
  36. 2025Clustering Discourses: Racial Biases in Short Stories about Women Generated by Large Language Modelscited by 0
  37. 2026When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generationcited by 0
  38. 2026Same Chart, Different Story: Bias in Vision-Language Chart Interpretationcited by 0