Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 1 paper
Filter2

Model risks

Deception and scheming1Inappropriate refusal22

System type

Models and APIs1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Deception and schemingSystem type：Models and APIsTopic: Defenses and guardrailsClear all
  1. DefensesarXiv 2609.38645

    用探针引导微调对齐模型且不损失可监控性

    用持续更新的探针做微调，降低有害性并保持线性可监测性

    arXiv
    2609.38645
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Mistral 7B Instruct v0.1, Llama 3 8B Instruct Abliterated, Qwen3-14B
    Abstract持续重拟合的探针可降低有害性、提高诚实性，训练后概念仍能被线性探针读出。

    Probe-guided fine-tuning 把探针分数当作唯一对齐信号，用来推动 harmlessness 与 honesty，并检查训练后这些概念是否仍线性可读。

    Paper analysisRead analysis
You have reached the end