Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Model risks

Inappropriate refusal6Bias and discrimination3

Impact

Harmful content32Availability and reliability6

System type

Models and APIs6

Layer

Model layer6Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Model risks：Inappropriate refusalImpact：Availability and reliabilityLayer：Model layerClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  3. 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
  6. Analysis and theoryarXiv 2601.08668

    分析大语言模型在仇恨言论去毒中误拒行为的偏差

    分析 LLM 仇恨言论解毒误拒的群体偏差并测试跨语翻译缓解

    arXiv
    2601.08668
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o mini, GPT-3.5 turbo, Llama-3.1 8B and others9
    Abstract九个 LLM 在解毒任务上普遍误拒，国籍宗教政治类偏高。

    作者考察对齐后的 LLM 是否会拒绝可接受的仇恨言论解毒请求，并分析误拒是否随目标群体和语言变化。完全拒答与夹带说教的部分拒答都计入。设置是固定提示、九个 LLM、三个英文集和法德西中韩。

    Paper analysisRead analysis
You have reached the end