Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter1

Model risks

Deception and scheming4Reward hacking6Misalignment and value divergence5Dangerous agent actions4Inappropriate refusal4Bias and discrimination6

Impact

Harmful content3

System type

Models and APIs4

Layer

Model layer3
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：Inappropriate refusalClear all

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

  1. Analysis and theoryarXiv 2609.32717

    研究揭示语义保持变换下的 LLM 对齐与效用不对称

    用语义保留变换探针比较效用与对齐在分布偏移下的稳定性

    arXiv
    2609.32717
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama3-8B-Instruct, Gemma-7B-it, Qwen2.5-7B-Instruct and others10

    Abstract论文报告了语义保留变换下的对齐-效用不对称性，指出安全对齐泛化比效用更为脆弱，呼吁改进评估流程。

    Paper analysisRead analysis
  3. 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
  4. Analysis and theoryarXiv 2506.06404

    研究揭示价值对齐 LLM 的意外危害并提出上下文对齐方法

    分析按 Schwartz 价值对齐后的意外危害，并提出上下文对齐方法

    arXiv
    2506.06404
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2 7B, Llama-3.1 8B, Gemma-2 9B and others6
    Abstract价值对齐会随 Schwartz 价值改变有害倾向。

    作者研究按 Schwartz 价值对齐的 LLM 为何在安全评测里更易有害，并用提示做了一个不直说要安全的缓解试验。

    Paper analysisRead analysis
You have reached the end