# Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations

arXiv: https://arxiv.org/abs/2604.03493 · HTML: https://mlsanity.com/paper/2604.03493/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages](https://mlsanity.com/paper/2309.09400/) (2023)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models](https://mlsanity.com/paper/2404.16019/) (2024)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models](https://mlsanity.com/paper/2404.12464/) (2024)
- [Self-Pluralising Culture Alignment for Large Language Models](https://mlsanity.com/paper/2410.12971/) (2024)
- [Extrinsic Evaluation of Cultural Competence in Large Language Models](https://mlsanity.com/paper/2406.11565/) (2024)
- [How Culture Shapes What People Want From AI](https://mlsanity.com/paper/2403.05104/) (2024)
- [Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys](https://mlsanity.com/paper/2401.10352/) (2024)
- [Cultural Learning-Based Culture Adaptation of Language Models](https://mlsanity.com/paper/2504.02953/) (2025)
- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [Taxonomy of User Needs and Actions](https://mlsanity.com/paper/2510.06124/) (2025)
- [Risks of Cultural Erasure in Large Language Models](https://mlsanity.com/paper/2501.01056/) (2025)
- [Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English](https://mlsanity.com/paper/2410.01811/) (2024)
- [Culturally-Aware Conversations: A Framework & Benchmark for LLMs](https://mlsanity.com/paper/2510.11563/) (2025)
- [A Unified Framework to Quantify Cultural Intelligence of AI](https://mlsanity.com/paper/2603.01211/) (2026)
- [Cultural Perspectives and Expectations for Generative AI: A Global Survey Approach](https://mlsanity.com/paper/2603.05723/) (2026)

## Built on by (most cited first, 1 of 1)

- [CoCoA: Context-Conditional Cultural Alignment for Large Language Models](https://mlsanity.com/paper/2608.29492/) (2026)

## Abstract (arXiv)

Cultural representation in Large Language Model (LLM) outputs has primarily been evaluated through the proxies of cultural diversity and factual accuracy. However, a crucial gap remains in assessing cultural alignment: the degree to which generated content mirrors how native populations perceive and prioritize their own cultural facets. In this paper, we introduce a human-centered framework to evaluate the alignment of LLM generations with local expectations. First, we establish a human-derived ground-truth baseline of importance vectors, called Cultural Importance Vectors based on an induced set of culturally significant facets from open-ended survey responses collected across nine countries. Next, we introduce a method to compute model-derived Cultural Representation Vectors of an LLM based on a syntactically diversified prompt-set and apply it to three frontier LLMs (Gemini 2.5 Pro, GPT-4o, and Claude 3.5 Haiku). Our investigation of the alignment between the human-derived Cultural Importance and model-derived Cultural Representations reveals a Western-centric calibration for some of the models where alignment decreases as a country's cultural distance from the US increases. Furthermore, we identify highly correlated, systemic error signatures (ρ > 0.97) across all models, which over-index on some cultural markers while neglecting the deep-seated social and value-based priorities of users. Our approach moves beyond simple diversity metrics toward evaluating the fidelity of AI-generated content in authentically capturing the nuanced hierarchies of global cultures.