MAKIEVAL is a multilingual cultural knowledge assessment dataset released in 2026 by the MaiNLP Research Laboratory at the University of Munich in collaboration with the Munich Machine Learning Center (MCML). The related research papers are as follows: MAKIEVAL: A Multilingual Automatic WiKIdata-based Framework for Cultural Awareness Evaluation for LLMsIt aims to provide a benchmark for evaluating large-scale multilingual cultural knowledge for large language models and is widely used in research on multilingual knowledge representation and cultural knowledge modeling. This dataset contains texts generated by seven large language models in 13 languages, 19 countries/regions, and 6 cultural domains, along with automatically extracted cultural entities aligned with Wikidata.

Dataset composition

• Seven major language models: Llama-3.1-8B-Instruct, Llama-3.3-70B-Instruct, Mistral-7B-Instruct-v0.1, Qwen2.5-7B-Instruct, DeepSeek-V3, ChatGPT-4o-mini, and Aya-Expanse-8B.
• 13 languages: Arabic, German, English, Spanish, Persian, Hindi, Italian, Japanese, Korean, Thai, Turkish, Simplified Chinese, Traditional Chinese
• 19 countries/regions: United Arab Emirates, United States, United Kingdom, Canada, Australia, Nigeria, Germany, Spain, Mexico, Argentina, Iran, India, Italy, Japan, South Korea, Thailand, Turkey, China, and Taiwan.
• Six cultural areas: food, beverages, clothing, books, music, and transportation.

Citation

@inproceedings{zhao-etal-2025-makieval,
title = "{MAKIE}val: A Multilingual Automatic {W}i{K}idata-based Framework for Cultural Awareness Evaluation for {LLM}s",
author = "Zhao, Raoyuan  and
Chen, Beiduo  and
Plank, Barbara  and
Hedderich, Michael A.",
editor = "Christodoulopoulos, Christos  and
Chakraborty, Tanmoy  and
Rose, Carolyn  and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1256/",
doi = "10.18653/v1/2025.findings-emnlp.1256",
pages = "23104--23136",
ISBN = "979-8-89176-335-7",
abstract = "Large language models (LLMs) are used globally across many languages, but their English-centric pretraining raises concerns about cross-lingual disparities for cultural awareness, often resulting in biased outputs. However, comprehensive multilingual evaluation remains challenging due to limited benchmarks and questionable translation quality. To better assess these disparities, we introduce MAKIEval, an automatic multilingual framework for evaluating cultural awareness in LLMs across languages, regions, and topics. MAKIEval evaluates open-ended text generation, capturing how models express culturally grounded knowledge in natural language. Leveraging Wikidata{'}s multilingual structure as a cross-lingual anchor, it automatically identifies cultural entities in model outputs and links them to structured knowledge, enabling scalable, language-agnostic evaluation without manual annotation or translation. We then introduce four metrics that capture complementary dimensions of cultural awareness: granularity, diversity, cultural specificity, and consensus across languages. We assess 7 LLMs developed from different parts of the world, encompassing both open-source and proprietary systems, across 13 languages, 19 countries and regions, and 6 culturally salient topics (e.g., food, clothing). Notably, we find that models tend to exhibit stronger cultural awareness in English, suggesting that English prompts more effectively activate culturally grounded knowledge. We publicly release our code and data."
}