Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

Defenses and guardrails · Papers

Found 1 paper
Filter2

Model risks

Inappropriate refusal1

Layer

Prompt layer1Model layer9Training and data layer12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Inappropriate refusalLayer：Prompt layerTopic: Defenses and guardrailsClear all
  1. DefensesarXiv 2609.05797

    论文发现安全监控器主要拦截模型本就会拒答的请求

    评估安全监视器并提出双侧梯级微调以减少会答有害请求的漏检

    arXiv
    2609.05797
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Gemma-4-31B-IT, Qwen3-32B, Llama Guard 3 8B and others6

    Abstract论文发现安全监视器大多拦截模型已拒答请求，指出明确度偏差是共性原因，并通过双侧梯级微调提升回答请求的召回表现。

    Paper analysisRead analysis
You have reached the end