NCSOFT/K-MMBench
收藏Hugging Face2025-07-25 更新2024-12-14 收录
下载链接：
https://hf-mirror.com/datasets/NCSOFT/K-MMBench
下载链接
链接失效反馈官方服务：
资源简介：
K-MMBench是一个专门用于评估视觉-语言模型的韩语数据集，它是MMBench的韩语版本。该数据集通过将MMBench的`dev`子集翻译成韩语，并经过人工审查以确保自然性，从而开发出一个专门针对韩语的鲁棒评估基准。数据集包含20个评估维度的问题，如身份推理、图像情感和属性识别等，并采用了MMBench提出的***CircularEval Strategy***以确保公平评估。
K-MMBench is a Korean adaptation of the MMBench designed for evaluating vision-language models. By translating the `dev` subset of MMBench into Korean and carefully reviewing its naturalness through human inspection, we developed a novel robust evaluation benchmark specifically for the Korean language. K-MMBench consists of questions across 20 evaluation dimensions, such as identity reasoning, image emotion, and attribute recognition, allowing a thorough evaluation of model performance in Korean. To ensure a fair evaluation, we adopt the ***CircularEval Strategy*** as proposed by the MMBench benchmark.
提供机构：
NCSOFT
