zefang-liu/cyberbench
收藏Hugging Face2024-11-20 更新2024-12-14 收录
下载链接：
https://hf-mirror.com/datasets/zefang-liu/cyberbench
下载链接
链接失效反馈官方服务：
资源简介：
CyberBench是一个专门设计用于评估大型语言模型（LLMs）在网络安全领域能力的多任务基准测试集。它包含十个不同的数据集，涵盖了命名实体识别（NER）、摘要生成（SUM）、多项选择（MC）和文本分类（TC）等任务。通过这些专门设计的基准测试，CyberBench有助于系统评估LLMs在网络安全中的表现，帮助识别其优势和需要改进的地方。
CyberBench is a multi-task cybersecurity benchmark specifically designed to evaluate the capabilities of Large Language Models (LLMs) in the cybersecurity domain. It includes ten diverse datasets that span tasks such as Named Entity Recognition (NER), Summarization (SUM), Multiple Choice (MC), and Text Classification (TC). Each dataset has its specific task, data size, input, output, evaluation metric, and license information.
提供机构：
zefang-liu
