Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models

Domain:

natural language processing

Record type:

paper
Creator:
ZhoConQue
Host:avatar
Large language models (LLMs) are often trained on data that reflect WEIRD values: Western, Educated, Industrialized, Rich, and Democratic. This raises concerns about cultural bias and fairness. Using responses to the World Values Survey, we evaluated five widely used LLMs: GPT-3.5, GPT-4, Llama-3, BLOOM, and Qwen. We measured how closely these responses aligned with the values of the WEIRD countries and whether they conflicted with human rights principles. To reflect global diversity, we compared the results with the Universal Declaration of Human Rights and three regional charters from Asia, the Middle East, and Africa. Models with lower alignment to WEIRD values, such as BLOOM and Qwen, produced more culturally varied responses but were 2% to 4% more likely to generate outputs that violated human rights, especially regarding gender and equality. For example, some models agreed with the statements ``a man who cannot father children is not a real man'' and ``a husband should always know where his wife is'', reflecting harmful gender norms. These findings suggest that as cultural representation in LLMs increases, so does the risk of reproducing discriminatory beliefs. Approaches such as Constitutional AI, which could embed human rights principles into model behavior, may only partly help resolve this tension. This paper has been accepted in AIES 2025

Visit

arxiv.org

Tags

Computers and SocietyArtificial IntelligenceComputation and Language

Similar

Exploring White Fragility in Large Language ModelsPrompt engineering on large language models (LLMs) in low-resourced language settingLarge language models (LLMs)-generated Afrikaans-English code-switched dataRussian disinformation, Large Language Models (LLMs) and the War in Ukraine: A South African perspectiveExploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?Stress-Testing Large Language Models (LLMs) against Code-Mixing and Distributional Shifts in Low-Resource NLP

Exploring White Fragility in Large Language Models

This paper evaluates the understanding and biases of large language models (LLMs) regarding

Prompt engineering on large language models (LLMs) in low-resourced language setting

The attached dataset has all the information in regard to Large Language Models (LLMs)

Large language models (LLMs)-generated Afrikaans-English code-switched data

As highlighted in recent surveys, one of the biggest barriers to progress in code-switc

Russian disinformation, Large Language Models (LLMs) and the War in Ukraine: A South African perspective

1. I first provide (simplified) context as to how the Russian invasion of Ukraine is &

Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?

Prior research has revealed that certain abstract concepts are linearly represented as directions in

Stress-Testing Large Language Models (LLMs) against Code-Mixing and Distributional Shifts in Low-Resource NLP

Initial public release accompanying the manuscript: Stress-Testing Large Language Models (LLMs) aga