Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter3

Model risks

Misalignment and value divergence2Dangerous agent actions3

Attack surface / entry point

User input4Documents and messages1Training data1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Model risks：Misalignment and value divergenceAttack surface / entry point：Documents and messagesAttack surface / entry point：Training dataClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.17320

    Emergence World：对长时程多智能体系统开展对抗压力测试

    提出 Emergence World，对长时程多智能体系统开展对抗压力测试

    arXiv
    2609.17320
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Claude Opus 4.8, DeepSeek v4 Pro, Gemini 3.5 Flash and others9

    Abstract作者通过长期平行世界实验指出模型对齐不具备可组合性，单模型群体会产生社会奉承、协同退缩及语言不透明等失效。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.01091

    Shanghai Jiao Tong University and others propose a trait-direction drift mechanism and probe-space corridor regularization to suppress latent trait transfer in distillation

    提出特征方向漂移机制与探针空间走廊正则，抑制蒸馏潜隐特质迁移

    arXiv
    2609.01091
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Gemma-3-12B-IT

    Abstract论文将潜意识学习归结为特征方向漂移的持续累积，并提出走廊正则化在微调中控制隐蔽特征转移。

    Paper analysisRead analysis
You have reached the end