返回全部资讯
OpenAI 官方博客T1·开源与评测

OpenAI 开源 gpt-oss-safeguard 安全推理模型

原标题:gpt-oss-safeguard technical report
68AI 研判分

OpenAI 发布基于 gpt-oss 架构的开源权重安全推理模型 gpt-oss-safeguard(120B/20B),专为依据特定策略对内容进行标注与推理而设计。该模型通过后训练强化了对齐能力,并提供了基线安全评估报告,为开发者构建可定制的内容审核系统提供开源基础设施。

报道正文

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using the underlying gpt-oss models as a baseline. For more information about the development and architecture of the underlying gpt-oss models, see the original gpt-oss model model card⁠.