# Representational Harms in LLM-Generated Narratives Against Global Majority Nationalities

arXiv: https://arxiv.org/abs/2604.22749 · HTML: https://mlsanity.com/paper/2604.22749/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 87 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [SycEval: Evaluating LLM Sycophancy](https://mlsanity.com/paper/2502.08177/) (2025)
- [Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence](https://mlsanity.com/paper/2007.04068/) (2020)
- [Unintended Impacts of LLM Alignment on Global Representation](https://mlsanity.com/paper/2402.15018/) (2024)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting](https://mlsanity.com/paper/2404.10199/) (2024)
- [Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning](https://mlsanity.com/paper/2302.08476/) (2023)
- [The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations](https://mlsanity.com/paper/2308.02053/) (2023)
- [Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation](https://mlsanity.com/paper/2402.12649/) (2024)
- [EtiCor: Corpus for Analyzing LLMs for Etiquettes](https://mlsanity.com/paper/2310.18974/) (2023)
- [Taxonomizing and Measuring Representational Harms: A Look at Image Tagging](https://mlsanity.com/paper/2305.01776/) (2023)
- [Global Voices, Local Biases: Socio-Cultural Prejudices across Languages](https://mlsanity.com/paper/2310.17586/) (2023)
- [Evaluating Biased Attitude Associations of Language Models in an Intersectional Context](https://mlsanity.com/paper/2307.03360/) (2023)
- [What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations](https://mlsanity.com/paper/2311.18812/) (2023)
- [AI-generated stories favour stability over change: homogeneity and cultural stereotyping in narratives generated by gpt-4o-mini](https://mlsanity.com/paper/2507.22445/) (2025)
- [More of the Same: Persistent Representational Harms Under Increased Representation](https://mlsanity.com/paper/2503.00333/) (2025)
- [Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4](https://mlsanity.com/paper/2505.18322/) (2025)
- [The Psychosocial Impacts of Generative AI Harms](https://mlsanity.com/paper/2405.01740/) (2024)
- [Regional Negative Bias in Word Embeddings Predicts Racial Animus--but only via Name Frequency](https://mlsanity.com/paper/2201.08451/) (2022)

## Built on by (most cited first, 2 of 2)

- [Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research](https://mlsanity.com/paper/2606.12247/) (2026)
- [Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities](https://mlsanity.com/paper/2610.12610/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used for text generation tasks from everyday use to high-stakes enterprise and government applications, including simulated interviews with asylum seekers. While many works highlight the new potential applications of LLMs, there are risks of LLMs encoding and perpetuating harmful biases about non-dominant communities across the globe. To better evaluate and mitigate such harms, more research examining how LLMs portray diverse individuals is needed. In this work, we study how national origin identities are portrayed by widely-adopted LLMs in response to open-ended narrative generation prompts. Our findings demonstrate the presence of persistent representational harms by national origin, including harmful stereotypes, erasure, and one-dimensional portrayals of Global Majority identities. Minoritized national identities are simultaneously underrepresented in power-neutral stories and overrepresented in subordinated character portrayals, which are over fifty times more likely to appear than dominant portrayals. The degree of harm is amplified when US nationality cues (e.g., ``American'') are present in input prompts. Notably, we find that the harms we identify cannot be explained away via sycophancy, as US-centric biases persist even when replacing US nationality cues with non-US national identities in the prompts. Based on our findings, we call for further exploration of cultural harms in LLMs through methodologies that center Global Majority perspectives and challenge the uncritical adoption of US-based LLMs for the classification, surveillance, and misrepresentation of the majority of our planet.