CLIcK

CLIcK是一个专注于韩国文化和语言智能的大型评估数据集，由韩国科学技术院创建。该数据集包含1995个问答对，数据来源于官方韩国考试和教科书，分为语言和文化两大类，进一步细分为11个子类别。数据集的创建过程包括数据收集、验证和分类，确保了数据的高质量和相关性。CLIcK主要用于评估大型语言模型在理解和处理韩国文化和语言方面的能力，旨在解决现有数据集在韩国文化和语言评估方面的不足。

CLIcK is a large-scale evaluation dataset focused on Korean culture and language intelligence, created by the Korea Advanced Institute of Science and Technology. It contains 1995 question-answer pairs sourced from official Korean examinations and textbooks, and is divided into two main categories: language and culture, which are further subdivided into 11 subcategories. The dataset's development process includes data collection, validation and classification, ensuring high data quality and relevance. CLIcK is primarily used to evaluate the capabilities of Large Language Models (LLMs) in understanding and processing Korean culture and language, aiming to address the deficiencies of existing datasets for Korean culture and language evaluation.