评估单语和多语大型语言模型在希腊语问答中的表现：DemosQA基准

Recent advancements in Natural Language Processing and Deep Learning have led to the development of Large Language Models (LLMs), which have significantly improved performance across various tasks, including Question Answering (QA). However, existing research has predominantly focused on high-resourced languages, such as English, with recent attention shifting towards multilingual models. These models often exhibit a training data bias towards a limited number of popular languages or rely on transfer learning from high-resourced to low-resourced languages, potentially misrepresenting social, cultural, and historical contexts. To address this issue, monolingual LLMs have been developed for under-resourced languages, aiming to enhance their performance in specific linguistic environments and promote diversity and accuracy in QA systems. This study evaluates the effectiveness of these models in Greek Question Answering tasks using the DemosQA benchmark.