# Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment

arXiv: https://arxiv.org/abs/2505.21548 · HTML: https://mlsanity.com/paper/2505.21548/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 25 May 2025.

## Builds on (most cited first, 21 of 21)

- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (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)
- [Re-imagining Algorithmic Fairness in India and Beyond](https://mlsanity.com/paper/2101.09995/) (2021)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia](https://mlsanity.com/paper/2305.11844/) (2023)
- [Multilingual Language Models are not Multicultural: A Case Study in Emotion](https://mlsanity.com/paper/2307.01370/) (2023)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?](https://mlsanity.com/paper/2501.15463/) (2025)
- [NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models](https://mlsanity.com/paper/2404.12464/) (2024)
- [Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting](https://mlsanity.com/paper/2406.11661/) (2024)
- [The Case for "Thick Evaluations" of Cultural Representation in AI](https://mlsanity.com/paper/2503.19075/) (2025)
- [Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi](https://mlsanity.com/paper/2504.06011/) (2025)
- [Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness](https://mlsanity.com/paper/2502.09637/) (2025)

## Built on by (most cited first, 10 of 10)

- [The Culture Funnel: You Can't Align What isn't in the Data](https://mlsanity.com/paper/2606.13808/) (2026)
- [Assessing the Pedagogical Readiness of Large Language Models as AI Tutors in Low-Resource Contexts: A Case Study of Nepal's K-10 Curriculum](https://mlsanity.com/paper/2604.09619/) (2026)
- [AI-Assisted Systematization for Evaluating GenAI Systems](https://mlsanity.com/paper/2605.26001/) (2026)
- [Benchmarking Frontier LLMs on Arabic Cultural and Sociolinguistic Knowledge: A Cross-Evaluation Framework with Human SME Ground Truth](https://mlsanity.com/paper/2607.00139/) (2026)
- [PLURAL: A Global Dataset for Value Alignment](https://mlsanity.com/paper/2607.08034/) (2026)
- [NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama](https://mlsanity.com/paper/2606.17391/) (2026)
- [Rethinking Indic AI from a Lens of Cultural Heritage Preservation](https://mlsanity.com/paper/2607.06544/) (2026)
- [Same violence, different answer: how AI responds to coercive control against women across languages](https://mlsanity.com/paper/2608.01436/) (2026)
- [Computational Orientalism: Measuring Structural Discourse Bias in Large Language Models Using the Middle East Cultural Sensitivity Score (MECSS)](https://mlsanity.com/paper/2608.18100/) (2026)
- [Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities](https://mlsanity.com/paper/2608.29209/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are used worldwide, yet exhibit Western cultural tendencies. Many countries are now building ``regional'' or ``sovereign'' LLMs, but it remains unclear whether they reflect local values and practices or merely speak local languages. Using India as a case study, we evaluate six Indic and six global LLMs on two dimensions -- values and practices -- grounded in nationally representative surveys and community-sourced QA datasets. Across tasks, Indic models do not align better with Indian norms than global models; in fact, a U.S. respondent is a closer proxy for Indian values than any Indic model. We further run a user study with 115 Indian users and find that writing suggestions from both global and Indic LLMs introduce Westernized or exoticized writing. Prompting and regional fine-tuning fail to recover alignment and can even degrade existing knowledge. We attribute this to scarce culturally grounded data, especially for pretraining. We position cultural evaluation as a first-class requirement alongside multilingual benchmarks and offer a reusable, community-grounded methodology. We call for native, community-authored corpora and thickxwide evaluations to build truly sovereign LLMs.