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

Reward hacking14Bias and discrimination1

System type

Models and APIs1

System component

Guardrails and judges1
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 discriminationSystem type：Models and APIsSystem component：Guardrails and judgesClear all

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

  1. Analysis and theoryarXiv 2609.20779

    研究称 GPT 系列安全训练把性别歧视转化而非消除

    提出 harm laundering，证明安全训练改写而非消除性别歧视

    arXiv
    2609.20779
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    gpt2, gpt2-medium, gpt2-large and others15
    AbstractGPT 谱系上毒性下降与表征伤害上升并存。

    Wyer、Black 与 Al Moubayed 用 OpenAI GPT 谱系检验：毒性分数下降是否等于歧视减少。 他们的答案是否定的，并把“显性伤害被改写成评测指标看不见的形式”称为 harm laundering。

    Paper analysisRead analysis
You have reached the end