Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter6

Model risks

Reward hacking5Misalignment and value divergence2Dangerous agent actions22Inappropriate refusal2

Defense type

Model hardening3Inference-time intervention10Instruction–data separation3Permissions and approval1Monitoring and auditing5

Layer

Model layer2Application layer2
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.
Model risks：Misalignment and value divergenceModel risks：Inappropriate refusalDefense type：Instruction–data separationDefense type：Permissions and approvalLayer：Model layerLayer：Application layerClear all

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

  1. InterpretabilityarXiv 2610.13078

    Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs

    Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel

    arXiv
    2610.13078
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Qwen3-8B-Instruct and others18
    AbstractAttention updates are more readable for harmfulness, MLP updates write refusal, and Sentinel routes alerts using two-path signals.

    The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.

    Paper analysisRead analysis
  2. DefensesarXiv 2610.05162

    MemAdapter：用反事实适配缓解记忆诱发的谄媚

    提出 MemAdapter，在检索后约束记忆对智能体推理的影响

    arXiv
    2610.05162
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-5.6-sol, Qwen3-8B
    Abstract检索后三阶段调节记忆角色。

    MemAdapter 是给长期记忆智能体用的检索后调节框架，用来处理记忆诱发谄媚。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.15803

    研究者提出 k-robust 联盟对齐，用多智能体评审委托授权

    提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权

    arXiv
    2609.15803
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。

    委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。

    Paper analysisRead analysis
  4. Analysis and theoryarXiv 2506.06404

    研究揭示价值对齐 LLM 的意外危害并提出上下文对齐方法

    分析按 Schwartz 价值对齐后的意外危害，并提出上下文对齐方法

    arXiv
    2506.06404
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2 7B, Llama-3.1 8B, Gemma-2 9B and others6
    Abstract价值对齐会随 Schwartz 价值改变有害倾向。

    作者研究按 Schwartz 价值对齐的 LLM 为何在安全评测里更易有害，并用提示做了一个不直说要安全的缓解试验。

    Paper analysisRead analysis
You have reached the end