OpenUnlearning Benchmark

What is OpenUnlearning?

OpenUnlearning is an efficient and modular benchmark platform designed to support and drive research on "unlearning" in large language models (LLMs).

Released

2025-06-14

Evaluates

其他, Other, 大语言模型, LLM, 安全对齐, Safety Alignment, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/OpenUnlearning

OpenUnlearning paper and code

• Paper https://arxiv.org/abs/2401.06121
• Paper https://arxiv.org/abs/2403.03218
• Paper https://arxiv.org/abs/2407.06460
• Paper https://arxiv.org/abs/2506.12618
• Code https://github.com/locuslab/open-unlearning

Which sources cite OpenUnlearning?

• OpenUnlearning

Related 其他, Other, 大语言模型, LLM, 安全对齐, Safety Alignment, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard