zero-false-positive

#zero-false-positive

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 cs.LG ↗ · 2026-07-28 Cached

Semalith v1.4 is a compact 184M parameter DeBERTa-v3 safety classifier that excels at prompt-injection detection with zero false positives on benign agentic prompts, while also handling general harm and financial compliance in a single pass, outperforming Llama-Guard-3-8B at 44x fewer parameters.

0 favorites 0 likes

zero-false-positive

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

Submit Feedback