Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 2 papers
Filter2

Model risks

Misalignment and value divergence2Inappropriate refusal9

Layer

Model layer2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Misalignment and value divergenceLayer：Model layerTopic: Defenses and guardrailsClear all
  1. DefensesarXiv 2610.01170

    HeadEdit：通过冻结的 unembedding 矩阵校准语言模型行为

    提出 HeadEdit，经冻结 unembedding 做随输入变化的 logit 校正

    arXiv
    2610.01170
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Gemma-3-4B-IT, Llama-3.2-3B-Instruct and others4
    Abstract低秩 unembedding 校正抬高九个设置的总体准确率，并可部分预测 DPO 更新。

    HeadEdit 是一种不更新参数的行为校准方法，作用点是冻结的 unembedding，而不是中间层残差或新的梯度优化。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.36657

    Constitutional adapters：用推理期干预防御越狱与失准

    提出 Constitutional adapters，蒸馏宪法行为以缓解越狱与失准

    arXiv
    2609.36657
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3.5-4B, Llama-3.1-8B-Instruct, Gemma-4-E4B and others4

    Abstract差分宪法适配器在长上下文和多轮上更稳，并可按 α 换取遵从。

    Paper analysisRead analysis
You have reached the end