Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Model risks

Inappropriate refusal2

Defense type

Instruction–data separation2

Attack surface / entry point

User input2
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 refusalDefense type：Instruction–data separationAttack surface / entry point：User inputClear all

Another 265papers 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
You have reached the end