BertaQA: How Much Do Language Models Know About Local Culture?
This addresses the gap in evaluating LLMs on non-anglocentric cultural topics, providing insights into knowledge transfer for low-resource languages, though it is incremental as it builds on existing evaluation methods.
The paper tackles the problem of evaluating language models on local cultural knowledge by introducing BertaQA, a parallel English-Basque trivia dataset, and finds that state-of-the-art LLMs struggle with Basque culture but improve with continued pre-training in Basque, showing knowledge transfer from low-resource to high-resource languages.
Large Language Models (LLMs) exhibit extensive knowledge about the world, but most evaluations have been limited to global or anglocentric subjects. This raises the question of how well these models perform on topics relevant to other cultures, whose presence on the web is not that prominent. To address this gap, we introduce BertaQA, a multiple-choice trivia dataset that is parallel in English and Basque. The dataset consists of a local subset with questions pertinent to the Basque culture, and a global subset with questions of broader interest. We find that state-of-the-art LLMs struggle with local cultural knowledge, even as they excel on global topics. However, we show that continued pre-training in Basque significantly improves the models' performance on Basque culture, even when queried in English. To our knowledge, this is the first solid evidence of knowledge transfer from a low-resource to a high-resource language. Our analysis sheds light on the complex interplay between language and knowledge, and reveals that some prior findings do not fully hold when reassessed on local topics. Our dataset and evaluation code are available under open licenses at https://github.com/juletx/BertaQA.