# Cultural Bias and Cultural Alignment of Large Language Models

arXiv: https://arxiv.org/abs/2311.14096 · HTML: https://mlsanity.com/paper/2311.14096/

## Key facts

- Cited by 149 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 10 of its 51 references that are in the map.
- First posted on arXiv 23 Nov 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 10 of 10)

- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models](https://mlsanity.com/paper/2304.03738/) (2023)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [Knowledge of cultural moral norms in large language models](https://mlsanity.com/paper/2306.01857/) (2023)
- [Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs](https://mlsanity.com/paper/2103.06076/) (2021)
- [Artificial intelligence in communication impacts language and social relationships](https://mlsanity.com/paper/2102.05756/) (2021)

## Built on by (most cited first, 30 of 149)

- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge](https://mlsanity.com/paper/2411.19799/) (2024)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [Inverse Constitutional AI: Compressing Preferences into Principles](https://mlsanity.com/paper/2406.06560/) (2024)
- [Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements](https://mlsanity.com/paper/2410.08968/) (2024)
- [CaLMQA: Exploring culturally specific long-form question answering across 23 languages](https://mlsanity.com/paper/2406.17761/) (2024)
- [CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge](https://mlsanity.com/paper/2404.06664/) (2024)
- [LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output](https://mlsanity.com/paper/2411.06032/) (2024)
- [Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://mlsanity.com/paper/2504.10191/) (2025)
- [Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA](https://mlsanity.com/paper/2405.07101/) (2024)
- [CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models](https://mlsanity.com/paper/2405.13974/) (2024)
- [Can LLMs make trade-offs involving stipulated pain and pleasure states?](https://mlsanity.com/paper/2411.02432/) (2024)
- [DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas](https://mlsanity.com/paper/2511.07338/) (2025)
- [An Evaluation of Estimative Uncertainty in Large Language Models](https://mlsanity.com/paper/2405.15185/) (2024)
- [Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models](https://mlsanity.com/paper/2412.16746/) (2024)
- [ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning](https://mlsanity.com/paper/2501.01031/) (2025)
- [CRAFT: Extracting and Tuning Cultural Instructions from the Wild](https://mlsanity.com/paper/2405.03138/) (2024)
- [Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions](https://mlsanity.com/paper/2601.22150/) (2026)
- [Computational Hermeneutics: Evaluating generative AI as a cultural technology](https://mlsanity.com/paper/2604.16403/) (2026)
- [Deterministic or probabilistic? The psychology of LLMs as random number generators](https://mlsanity.com/paper/2502.19965/) (2025)
- [Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensions](https://mlsanity.com/paper/2503.23688/) (2025)
- [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)
- [Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2510.24012/) (2025)
- [Antagonistic AI](https://mlsanity.com/paper/2402.07350/) (2024)
- [Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness](https://mlsanity.com/paper/2409.10825/) (2024)
- [Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essays](https://mlsanity.com/paper/2503.20062/) (2025)
- [CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization](https://mlsanity.com/paper/2504.08820/) (2025)

## Abstract (arXiv)

Culture fundamentally shapes people's reasoning, behavior, and communication. As people increasingly use generative artificial intelligence (AI) to expedite and automate personal and professional tasks, cultural values embedded in AI models may bias people's authentic expression and contribute to the dominance of certain cultures. We conduct a disaggregated evaluation of cultural bias for five widely used large language models (OpenAI's GPT-4o/4-turbo/4/3.5-turbo/3) by comparing the models' responses to nationally representative survey data. All models exhibit cultural values resembling English-speaking and Protestant European countries. We test cultural prompting as a control strategy to increase cultural alignment for each country/territory. For recent models (GPT-4, 4-turbo, 4o), this improves the cultural alignment of the models' output for 71-81% of countries and territories. We suggest using cultural prompting and ongoing evaluation to reduce cultural bias in the output of generative AI.