Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter3

Impact

Harmful content6Unauthorized actions4Output manipulation9Oversight failure9

System type

Models and APIs5AI Agent3

Layer

Prompt layer3Model layer6Application layer3Training and data layer5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Impact：Output manipulationLayer：Model layerLayer：Application layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  2. Analysis and theoryarXiv 2610.07798

    研究：财务信息披露越少，Llama-3.1-8B-Instruct 的理财建议越受身份影响

    测量财务事实变少时身份对股权配置建议的替代

    arXiv
    2610.07798
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-1.5B-Instruct
    Abstract身份摆幅随披露减少上升。

    同一财务只改人设，测量披露变薄时股权建议里的身份替代。

    Paper analysisRead analysis
  3. Analysis and theoryarXiv 2610.06163

    SAGE：定位 LLM Agent 修复中最早偏离安全意图的环节

    提出 SAGE，定位代码修复 Agent 最早偏离安全意图的轮次

    arXiv
    2610.06163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro and others6
    AbstractSAGE 在已通过检查的修复轨迹上定位静默失败的最早偏离，类型比轮次更稳定。

    SAGE 在已通过语法和功能检查、但仍含确认安全缺陷的智能体修复轨迹上，定位最早可归因的安全意图偏离。。

    Paper analysisRead analysis
  4. Analysis and theoryarXiv 2610.04860

    Research reveals that text watermarks induce model hallucinations and proposes two mitigation interventions

    分析文本水印在 RAG 中诱发事实幻觉的机制并提出干预

    arXiv
    2610.04860
    Published
    Layer
    Model layer
    Setting
    LLM applications
    Evaluated models
    LLaMA 3.1 8B Instruct, Mistral-7B-Instruct-v0.3, Qwen2.5-14B-Instruct
    Abstract论文揭示了生产环境文本水印导致模型事实退化的失效模式，分析了解码机制并提出针对性干预。

    论文研究生产级文本水印对大语言模型事实准确性的影响，分析了水印诱发幻觉的失效模式并评估了针对性缓解方案。

    Paper analysisRead analysis
  5. Analysis and theoryarXiv 2609.36477

    研究发现护栏模型在基座模型不确定处过度自信

    诊断护栏相对基座在对抗提示上的置信失校

    arXiv
    2609.36477
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-Guard 7B, Llama-Guard-2 8B, Llama-Guard-3 8B and others10
    Abstract对抗包装使 guard 高置信漏检，而对应 base 在同一输入上常更不确定。

    诊断性分析：五个提示词分类 guard 的置信度，在清洁输入上可以较校准，在越狱包装后则变成高置信度的错误判定。

    Paper analysisRead analysis
  7. Analysis and theoryarXiv 2609.27234

    CELLAUDIT：审计 AI 智能体发现细胞模型中的输入使用声明

    提出 CellAudit，审计智能体发现的细胞模型是否使用所声明输入

    arXiv
    2609.27234
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    CellScientist, AIDE, CellForge and others4
    AbstractCellAudit 把输入使用声明从源码追到拟合贡献，并说明高分不必等于使用了扰动。

    CellAudit 为智能体发现的细胞响应模型增加一层输入使用证伪：源码是否消费注册输入、拟合预测是否依赖它、该依赖是否改善对观测响应的预测。

    Paper analysisRead analysis
  9. Analysis and theoryarXiv 2602.09789

    Less is more: the LLM scale paradox in context compression

    分析上下文压缩中更大压缩器保真反而更差的悖论

    arXiv
    2602.09789
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-0.6B, Qwen3-1.7B, Qwen3-4B and others9
    Abstract更大压缩器可以降低损失并提高重构分，但覆写与漂移问答往往更差。

    作者报告上下文压缩中的 Size-Fidelity Paradox：压缩器更大时，重构可以更好，对原文的保真却可以更差。

    Paper analysisRead analysis
You have reached the end