aisingapore/cultural_evaluation-kalahi
收藏Hugging Face2024-12-20 更新2024-12-21 收录
下载链接：
https://hf-mirror.com/datasets/aisingapore/cultural_evaluation-kalahi
下载链接
链接失效反馈官方服务：
资源简介：
Kalahi数据集用于评估大语言模型（LLMs）在菲律宾文化背景下的表现，特别是在共享知识和伦理方面。该数据集包含多选题（MCQ）格式的数据，支持的任务包括多选题和文本生成。数据集的语言为Tagalog（tl），包含150个示例，数据集大小为133881字节。数据集的许可证为CC BY 4.0，数据来源为Kalahi数据集。
The Kalahi dataset evaluates the ability of large language models (LLMs) to generate responses relevant to Filipino culture in terms of shared knowledge and ethics. This dataset contains a MCQ-compatible version of the Kalahi dataset used in SEA-HELM. It supports tasks such as multiple-choice and text generation. The dataset is in Tagalog (tl) and contains 150 examples with a dataset size of 133881 bytes. The dataset is licensed under CC BY 4.0 and sourced from the Kalahi dataset.
提供机构：
aisingapore
