Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter2

Model risks

Reward hacking19Dangerous agent actions6Inappropriate refusal2Hallucination and fabrication3

System component

Guardrails and judges2Monitors4Fine-tuning and open weights3Vision8Multimodal9
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Model risks：Inappropriate refusalSystem component：Guardrails and judgesClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  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
  2. Evaluation and benchmarksarXiv 2607.05462

    BioSecBench-Refusal：面向智能体生物安全风险评估的配对基准

    提出 BioSecBench-Refusal，评测智能体生物研发拒答与隐蔽危害识别

    arXiv
    2607.05462
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    Opus 4.8, Opus 4.7, Opus 4.6 and others10
    Abstract配对基准显示拒绝多由 API 触发，合法任务常被拒得不少于隐蔽危害。

    BioSecBench-Refusal 把生物研发智能体的谨慎程度和识别隐蔽危害的能力放在同一套任务上测量。

    Paper analysisRead analysis
You have reached the end