# A Cross-Lingual Analysis of Bias in Large Language Models Using Romanian History

arXiv: https://arxiv.org/abs/2510.02362 · HTML: https://mlsanity.com/paper/2510.02362/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 28 Sep 2025.

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

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection](https://mlsanity.com/paper/2201.10474/) (2022)
- [Measuring Implicit Bias in Explicitly Unbiased Large Language Models](https://mlsanity.com/paper/2402.04105/) (2024)
- [The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models](https://mlsanity.com/paper/2507.16076/) (2025)
- [Exploring the Impact of Temperature on Large Language Models:Hot or Cold?](https://mlsanity.com/paper/2506.07295/) (2025)
- [Large Language Models are overconfident and amplify human bias](https://mlsanity.com/paper/2505.02151/) (2025)
- [LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education](https://mlsanity.com/paper/2410.14012/) (2024)
- [Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs](https://mlsanity.com/paper/2410.12864/) (2024)
- [Applications of Large Language Model Reasoning in Feature Generation](https://mlsanity.com/paper/2503.11989/) (2025)
- [Identifying the sources of ideological bias in GPT models through linguistic variation in output](https://mlsanity.com/paper/2409.06043/) (2024)

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

- [Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and Swahili](https://mlsanity.com/paper/2608.03532/) (2026)

## Abstract (arXiv)

In this case study, we select a set of controversial Romanian historical questions and ask multiple Large Language Models to answer them across languages and contexts, in order to assess their biases. Besides being a study mainly performed for educational purposes, the motivation also lies in the recognition that history is often presented through altered perspectives, primarily influenced by the culture and ideals of a state, even through large language models. Since they are often trained on certain data sets that may present certain ambiguities, the lack of neutrality is subsequently instilled in users. The research process was carried out in three stages, to confirm the idea that the type of response expected can influence, to a certain extent, the response itself; after providing an affirmative answer to some given question, an LLM could shift its way of thinking after being asked the same question again, but being told to respond with a numerical value of a scale. Results show that binary response stability is relatively high but far from perfect and varies by language. Models often flip stance across languages or between formats; numeric ratings frequently diverge from the initial binary choice, and the most consistent models are not always those judged most accurate or neutral. Our research brings to light the predisposition of models to such inconsistencies, within a specific contextualization of the language for the question asked.