Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter2

Model risks

Misalignment and value divergence2Dangerous agent actions5Hallucination and fabrication3

Defense type

Model hardening13Inference-time intervention6Detection and filtering2Monitoring and auditing3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 313papers have no tags yet and are not included in filtered results.
Model risks：Misalignment and value divergenceDefense type：Detection and filteringClear all

Another 313papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.07403

    针对 LLM 谄媚的纵深防御：记忆门控对激活诱导与记忆诱导谄媚的评估

    评测记忆门控对激活诱导与记忆诱导谄媚的防御效果

    arXiv
    2610.07403
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3 and others4
    Abstract作者称外部记忆过滤成立，数据未显示反向转向再有贡献。

    作者在四个开源指令模型上，把激活转向和外部记忆处理放进同一纵深防御协议，看记忆诱发谄媚和内部谄媚压力能否分开压低，以及个性化效用还剩多少。要处理的问题是：检索到的用户历史会推动模型顺从存储信念。只改外部上下文，并不直接动模型内部的谄媚表征。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.29429

    Jev 被用于零样本检测十类对齐失败，中位 AUROC 达 0.886

    提出 RLCDAlignBench，零样本检测多种对齐失败

    arXiv
    2609.29429
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Jev (jev-1.13.0)
    Abstract一次通用问题已能给多数对齐失败排序，大的误差来自状态和标签。

    RLCDAlignBench 测量用强化学习做校准决策的 Jev，能否当作对齐失败的零样本检测器。

    Paper analysisRead analysis
You have reached the end