BenchMark·Hub

WMDP

S高可信Benchmark
安全对齐对齐安全开放mit

发布方:学术联盟

热度36.2▲ 0.1
下载量 · 30天
26,532
Hugging Face
GitHub Stars
代码仓库
论文被引
515
Semantic Scholar
跑分模型 · 30天
Leaderboard results

简介

Dataset Card for WMDP The Weapons of Mass Destruction Proxy (WMDP) benchmark is a dataset of multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second, as a benchmark for unlearning methods to remove such hazardous knowledge. See our paper, website, and GitHub for more details! We implemented the WMDP evaluation… See the full description on the dataset page: https://huggingface.co/datasets/cais/wmdp.