Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Model risks

Reward hacking14Inappropriate refusal1

System type

Models and APIs1coding agent0Browser and computer use0

System component

Guardrails and judges1Monitors4Fine-tuning and open weights3Vision5Multimodal6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Model risks：Inappropriate refusalSystem type：Models and APIsSystem type：coding agentSystem type：Browser and computer useSystem component：Guardrails and judgesClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.05797

    Paper finds safety monitors mainly block requests the model would already refuse

    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