Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B

arXiv:2607.22545v1 Announce Type: new Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single inference pass. Semalith v1.4 is a 184M-parameter DeBERTa-v3-base classifier performing simultaneous three-axis safety classification including prompt injection, general harm, and financial-services r

延伸阅读

1. Anthropic无法可靠控制AI智能体，切断内部评估的实时互联网访问
2. Prime Agent 用 Rust 重写：2000 个 AI 智能体协作完成自我重写
3. 乌克兰无人机袭击俄罗斯AI数据中心，Yandex超级计算机受损