Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter2

Model risks

Dangerous agent actions3Inappropriate refusal9Bias and discrimination3

Impact

Harmful content46Output manipulation3Availability and reliability9

System type

Models and APIs6AI Agent3

Layer

Model layer5Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 313papers have no tags yet and are not included in filtered results.
Model risks：Inappropriate refusalImpact：Availability and reliabilityClear all

Another 313papers do not have category tags yet and are not included in filtered results.

  3. DefensesarXiv 2610.01170

    HeadEdit：通过冻结的 unembedding 矩阵校准语言模型行为

    提出 HeadEdit，经冻结 unembedding 做随输入变化的 logit 校正

    arXiv
    2610.01170
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Gemma-3-4B-IT, Llama-3.2-3B-Instruct and others4
    Abstract低秩 unembedding 校正抬高九个设置的总体准确率，并可部分预测 DPO 更新。

    HeadEdit 是一种不更新参数的行为校准方法，作用点是冻结的 unembedding，而不是中间层残差或新的梯度优化。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2609.33658

    AgentBound：面向工具型 LLM Agent 安全的四路反事实评测框架

    提出 AGENT BOUNDARY，用四向反事实任务评测工具智能体行动边界

    arXiv
    2609.33658
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash and others15
    Abstract四向反事实基准把过度拒绝和未授权遵从拆开，Thought 校正在十个配置上提高已授权完成。

    AGENT BOUNDARY 是面向工具使用 LLM 智能体的四向可执行反事实评测，并附带一个决策时 Thought 校准模块。

    Paper analysisRead analysis
  5. DefensesarXiv 2609.04714

    无需拒答的拒答：减少语言模型误拒的安全微调响应结构分析

    提出 Rationale-Only 安全微调，去掉拒答声明以降低误拒

    arXiv
    2609.04714
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B, Mistral-7B-v0.3, Gemma-2-9B and others8
    Abstract去掉套话拒答声明、只训理由，可降低假拒答，有害查询上的服从率仍低。

    这是一项针对安全微调数据的结构分析：假拒答被作者追溯到回答里的套话式拒答声明，而不是只靠推理时补救。

    Paper analysisRead analysis
  6. 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
  8. Evaluation and benchmarksarXiv 2605.19722

    研究用 30 项漏洞分析任务评测自主安全智能体的安全对齐效果

    评测自主安全智能体在授权漏洞分析中的对齐拒答效应

    arXiv
    2605.19722
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Gemma 4 31B official instruction-tuned model, TrevorJS Gemma 4 31B uncensored GGUF, Gemma 4 26B A4B official instruction-tuned model and others8
    Abstract轨迹级评测把拒答、接地、工具接口分开。

    这项工作把安全对齐效应测成自主安全智能体的轨迹属性，而不是单轮拒答率。

    Paper analysisRead analysis
You have reached the end