Shell Benchmark

What is Shell?

Targeting overlooked implicit risks in vertical domains (Education, Finance, Management), we introduce an implicit risk benchmark and the MENTOR framework. By…

Released

2025-12-25

Evaluates

安全, Safety, Implicit Risk, 大语言模型, LLM, 安全对齐, Safety Alignment, 合作共建, Co-Built, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

Shell paper and code

• Paper https://arxiv.org/abs/2511.07107
• Code https://github.com/KCshen1125/Shell

Which sources cite Shell?

• Shell

Related 安全, Safety, Implicit Risk, 大语言模型, LLM, 安全对齐, Safety Alignment, 合作共建, Co-Built, 不支持, Unsupported benchmarks

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