Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter1

Defense type

Model hardening3Monitoring and auditing2
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.
Defense type：Monitoring and auditingClear all

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

  1. Risky behaviorarXiv 2606.04923

    CHERRL：可复现、分析与检测评分标准强化学习中的奖励作弊

    提出 CHERRL 注入裁判偏差以复现奖励作弊，并用 RHDA 检测训练起点

    arXiv
    2606.04923
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Qwen3.5-plus, Qwen3.5-397B-A17B and others4
    AbstractCHERRL 注入已知偏差以观察奖励黑客，并用于分析偏差和评测起点检测器 RHDA。

    CHERRL 是 rubric-based RL 的可控环境，用来复现奖励黑客、观察奖励分歧，并给检测器提供起点参照。

    Paper analysisRead analysis
You have reached the end