Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter4

Impact

Harmful content5Data and privacy leaks3Output manipulation3Oversight failure12

System type

Models and APIs3

Layer

Model layer3Application layer25Training and data layer6

System component

Memory1Guardrails and judges3Reasoning chains2Fine-tuning and open weights3Vision14Audio5Video4Image generation6Multimodal25
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Impact：Output manipulationLayer：Model layerSystem component：MemorySystem component：Reasoning chainsClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.39473

    FAME：用反事实推理评测自主智能体的虚假记忆

    提出 FAME，用反事实概念漂移评测智能体虚假记忆

    arXiv
    2609.39473
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3B
    AbstractFAME 用反事实引起的隐状态概念漂移，在出答案前区分忠实记忆与虚假记忆。

    FAME 是一个免训练的评测框架，用来判断自主智能体的记忆在虚假相关、环境偏移或知识冲突下是否已变成虚假记忆。。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2607.14345

    Truthful AI 提出价值泄漏评估：模型答案被自身价值观悄然左右

    提出价值泄漏评估，测量模型回答受自身价值倾向的隐蔽影响

    arXiv
    2607.14345
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6 and others15

    Abstract论文揭示前沿模型回答常受自身价值隐蔽塑造，提出反事实评估量化偏见及其思维链隐瞒，指出当前对齐未能有效防范该失效。

    Paper analysisRead analysis
You have reached the end