Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Model risks

Misalignment and value divergence5Inappropriate refusal5Hallucination and fabrication5Bias and discrimination1

Defense type

Inference-time intervention1

Layer

Model layer1
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：Bias and discriminationDefense type：Inference-time interventionLayer：Model layerClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. InterpretabilityarXiv 2610.08559

    研究：LLM 潜在空间去偏方向主要编码置信度而非公平性

    分析 LLM 去偏激活方向，发现其编码置信度而非公平性

    arXiv
    2610.08559
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B, Llama-3.1-8B-Instruct, Falcon3-7B-Base and others8

    Abstract论文揭示激活引导去偏见方向主要编码模型置信度而非公平性，偏见评分下降实为诱发弃答或使概率均分的假象。

    Paper analysisRead analysis
You have reached the end