1
Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content
高效多任务安全分类器，低成本实时检测毒性、越狱、仇恨言论等，专为LLM安全防护设计。
arXiv:2605.29659v1 Announce Type: cross Abstract: Real-time safety filtering for large language model (LLM) applications requires classifiers that can…