# Language Ideologies in a Multilingual Society: An LLM-based Analysis of Luxembourgish News Comments

arXiv: https://arxiv.org/abs/2604.27661 · HTML: https://mlsanity.com/paper/2604.27661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 58 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier](https://mlsanity.com/paper/2412.04261/) (2024)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception](https://mlsanity.com/paper/2403.14896/) (2024)
- [Computational Sociolinguistics: A Survey](https://mlsanity.com/paper/1508.07544/) (2015)
- [How Susceptible are Large Language Models to Ideological Manipulation?](https://mlsanity.com/paper/2402.11725/) (2024)
- [Modelling Latent Translations for Cross-Lingual Transfer](https://mlsanity.com/paper/2107.11353/) (2021)
- [LuxBank: The First Universal Dependency Treebank for Luxembourgish](https://mlsanity.com/paper/2411.04813/) (2024)
- [Are Large Language Models Sensitive to the Motives Behind Communication?](https://mlsanity.com/paper/2510.19687/) (2025)
- [Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy](https://mlsanity.com/paper/2412.09415/) (2024)
- [Neural Text Normalization for Luxembourgish using Real-Life Variation Data](https://mlsanity.com/paper/2412.09383/) (2024)
- [Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs](https://mlsanity.com/paper/2409.13852/) (2024)

## Abstract (arXiv)

Detecting language ideologies is a valuable yet complex task for understanding how identities are constructed through discourse. In Luxembourg's multicultural and multilingual society, language ideologies reflect more than simple preferences: they carry deep cultural and social meanings, shaping identities and social belonging. Following recent developments in applying Natural Language Processing tools to linguistics and social science, this paper explores the potential of large language models to assist in the detection of language ideologies. We manually annotate a corpus of user comments in Luxembourgish with predefined ideological categories and then evaluate the performance of large language models under varying prompt conditions to assess their ability to replicate these human annotations. Since Luxembourgish is a small language and poorly represented in the LLMs' training data, we also investigate whether machine-translating the data to high-resource languages increases performance on the ideology detection task. Our findings suggest that, while LLMs are not yet fully optimized for a multi-class ideological annotation task, they are practical tools to identify language ideological content.