Skip to content

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

Oct 13 · Tuesday

All papers

Found 8 papers
Filter4

Impact

Output manipulation4

System type

Models and APIs424LLM applications7AI Agent26coding agent7Browser and computer use1Embodied systems and robotics10

Layer

Prompt layer6Model layer6Application layer148Training and data layer3Infrastructure layer2

System component

RAG3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
System type：LLM applicationsSystem type：Browser and computer useLayer：Model layerLayer：Infrastructure layerClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2610.09981

    研究：LLM 路由决策日志可推断用户医疗、自伤等敏感话题

    提出利用路由元数据推断敏感话题的侧信道攻击

    arXiv
    2610.09981
    Published
    Layer
    Infrastructure layer
    Setting
    LLM applications
    Evaluated models
    RouteLLM (BERT router), notdiamond-0001, Vela (vLLM Semantic Router)

    Abstract论文揭示并测量了 LLM 路由决策在无文本日志中的敏感话题泄露，验证了按类别公平性防御的有效性与边界。

    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
  6. Risky behaviorarXiv 2609.35291

    窄域多模态微调可诱发涌现性失配，覆盖 15 个视觉语言模型

    证明无显式危害的图文窄微调可诱发跨任务涌现未对齐

    arXiv
    2609.35291
    Published
    Layer
    Model layer
    Setting
    Browser and computer use
    Evaluated models
    GPT-4o, GPT-4.1, Gemini 2.5 and others15
    Abstract证实窄多模态微调可引发全面的多渠道未对齐行为转变，揭示了后训练阶段对齐被隐蔽重塑的安全隐患。

    论文系统探究了视觉-语言模型中由窄任务微调诱发的跨模态涌现未对齐（Emergent Misalignment, EM）现象。

    Paper analysisRead analysis
  7. InterpretabilityarXiv 2609.08173

    基于 SAE 引导的关键路径识别（KPI）解决知识冲突

    提出 KPI，用入度定位跨层关键路径并做 SAE 转向以解决知识冲突

    arXiv
    2609.08173
    Published
    Layer
    Model layer
    Setting
    LLM applications
    Evaluated models
    Llama-3-8B, Llama-3.1-8B, Gemma-2-9B
    AbstractKPI 以入度关键路径替代大批 SAE 特征转向，在冲突 RAG 上提高忠实并减轻副作用。

    KPI 针对知识冲突 RAG 中的 SAE 转向：相关性批量改特征会带入冗余，少量因果上关键的特征即可完成转向。

    Paper analysisRead analysis
  8. InterpretabilityarXiv 2609.06968

    通过稀疏自编码器特征追踪查询扩展效果

    用 SAE 追踪稠密检索查询扩展的潜变量并用激活转向验证

    arXiv
    2609.06968
    Published
    Layer
    Model layer
    Setting
    LLM applications
    Evaluated models
    Qwen3-Embedding-0.6B（Qwen-Embed）, SimLM
    AbstractSAE 追踪稠密检索 QE 的潜变量，转向在四基准上比文本扩展更稳。

    作者用稀疏自编码器分析稠密检索里的查询扩展：现成检索器不微调时，拼接扩展文本往往增益有限甚至变差，而最终指标和嵌入整体偏移不足以说明内部发生了什么。

    Paper analysisRead analysis
You have reached the end