Semalith v1.4 Packs SOTA Prompt‑Injection Detection into 184M‑Parameter Model
Semalith v1.4 is a 184M‑parameter DeBERTa‑v3‑base classifier that simultaneously flags prompt‑injection, general harm, and BFSI regulatory issues. It outperforms Llama‑Guard‑3‑8B on all prompt‑injection benchmarks while using 44× fewer parameters and achieving zero false‑positives on benign agentic prompts.