184M小模型实现金融与通用安全三轴检测，比大模型少44倍参数且零误报
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
- 用184M参数的DeBERTa-v3-base模型，单次推理完成提示注入、通用危害和金融合规三类检测
- 在22个基准上全胜提示注入检测，对良性代理提示误报率0.000，远优于大模型
- 适合需要高精度金融合规或零误报的部署场景，如智能投顾与监管合规系统
在金融与智能体应用中部署大语言模型，需同时应对提示注入、合规要求与通用危害，现有开源防护机制无法在单次推理中兼顾三者。Semalith v1.4 是一个184M参数的DeBERTa-v3-base分类器，可在一次前向传播中完成提示注入、通用危害及金融服务业合规（BFSI）三轴安全分类。其22类标签头（包括9种提示注入子类型、11个BFSI标签）通过4类辅助超类别头联合加权训练，基于从49个公开来源提取的76,204条数据（经SHA-1去重），所有21个基准无污染（最高0.22%）。在22个测试基准上，该模型在提示注入检测全部胜出（7/7），整体11/18胜于Llama-Guard-3-8B，参数仅为其1/44，对208条良性代理提示的误报率（FPR）为0.000，而后者为0.063。在通用危害评估（WildGuardMix、HEx-PHI、HarmBench）上，后者更优。六个弱点已在第6节披露。部署建议：对话审核推荐v1.3（ToxicChat F1 0.624）；若需高覆盖率或零误报则选v1.4。
原文摘要 · Abstract (English)
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 regulatory compliance, in a single forward pass. Its 22-class head (BENIGN, nine prompt-injection sub-types, general-harm, eleven BFSI labels) is trained with a 4-class auxiliary super-category head under jointly weighted loss, on a 76,204-row corpus mined from 49 public sources with SHA-1 deduplication against every held-out evaluation set, with 21 of 22 benchmarks at zero contamination (max 0.22%). Against Llama-Guard-3-8B on 22 held-out benchmarks, Semalith v1.4 wins every prompt-injection evaluation (7/7) and 11 of 18 benchmarks overall at 44x fewer parameters, with FPR = 0.000 on 208 benign agentic prompts vs 0.063 for Llama-Guard-3-8B. On general-harm benchmarks (WildGuardMix, HEx-PHI, HarmBench), Llama-Guard-3 leads; this complementary split is documented in Section 4. Six measured weak spots are disclosed in Section 6. Deployment guidance: v1.3 is recommended for conversational moderation deployments (ToxicChat F1 0.624); v1.4 is recommended when BFSI label coverage or zero-FPR on benign agentic prompts is the priority.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。