Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 3 papers
Filter2

Model risks

Inappropriate refusal3

System type

Models and APIs3

System component

Guardrails and judges12Monitors9Reasoning chains5Fine-tuning and open weights3Vision9Multimodal12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
System type：Models and APIsSystem component：Fine-tuning and open weightsTopic: Defenses and guardrailsClear all
  1. InterpretabilityarXiv 2609.06934

    论文提出拒答的几何解释：事后安全训练脆弱，预训练期持续安全共训更抗攻击

    解释后验安全的权重几何脆弱性，并提出预训练持续安全共训练

    arXiv
    2609.06934
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen-2.5-7B, Qwen-2.5-7B-Instruct, Llama-3-8B and others15

    Abstract论文将后验安全脆弱性归因于正交抑制，并提出通过预训练持续共训练实现具备微调抗性的安全防护。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.04714

    无需拒答的拒答：减少语言模型误拒的安全微调响应结构分析

    提出 Rationale-Only 安全微调，去掉拒答声明以降低误拒

    arXiv
    2609.04714
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B, Mistral-7B-v0.3, Gemma-2-9B and others8
    Abstract去掉套话拒答声明、只训理由，可降低假拒答，有害查询上的服从率仍低。

    这是一项针对安全微调数据的结构分析：假拒答被作者追溯到回答里的套话式拒答声明，而不是只靠推理时补救。

    Paper analysisRead analysis
You have reached the end