New 184M-parameter safety classifier Semalith v1.4 outperforms Llama-Guard-3-8B on prompt injection

By PulseAugur Editorial · [1 sources] · 2026-07-28 04:00

Researchers have introduced Semalith v1.4, a new safety classifier designed for large language models. This 184M-parameter model, built on DeBERTa-v3-base, excels at detecting prompt injection attacks and ensuring regulatory compliance, particularly within financial services. In evaluations, Semalith v1.4 outperformed Llama-Guard-3-8B on prompt-injection benchmarks while using significantly fewer parameters, though Llama-Guard-3-8B showed stronger performance on general harm detection. AI

IMPACT This research offers a more parameter-efficient approach to LLM safety, potentially reducing deployment costs and improving prompt injection detection.

RANK_REASON The cluster describes a new academic paper detailing a novel safety classifier model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

paper
safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New 184M-parameter safety classifier Semalith v1.4 outperforms Llama-Guard-3-8B on prompt injection

COVERAGE [1]

arXiv cs.AI TIER_1 English(EN) · Tejasvi C. Addagada · 2026-07-28 04:00

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: cross 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 …

COVERAGE [1]

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

RELATED ENTITIES

RELATED TOPICS