SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing
SafePyramid benchmark evaluates guardrail systems' ability to identify safety violations through in-context policy specification across multiple domains and complexity levels.
Hugging Face · Daily Papers
·Jiacheng Zhang, Haoyu He
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Jiacheng Zhang, Haoyu He, Sen Zhang, Shen Wang, Xiaolei Xu, Yuhao Sun
- 3 upvotes da comunidade
- Temas: guardrails, in-context policy guardrailing, safety benchmark, policy specifications, multi-turn conversations, natural-language rules
Resumo
Resumo original (em inglês), extraído do paper:
SafePyramid benchmark evaluates guardrail systems' ability to identify safety violations through in-context policy specification across multiple domains and complexity levels.Onde ler
// relacionados
Leia também
Modelo
nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16
Blog
OpenClaw is finally available on Android and iOS
Blog
Claude Science is Anthropic’s newest flagship product
Blog