Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Defense type

Inference-time intervention3Instruction–data separation0Monitoring and auditing2

Layer

Model layer2

System component

Monitors14Reasoning chains2Fine-tuning and open weights3Vision3Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationDefense type：Monitoring and auditingLayer：Model layerSystem component：Reasoning chainsClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.02741

    研究系统评估循环语言模型的思维链可监控性

    系统评估循环语言模型加深 loop 后的 CoT 可监控性

    arXiv
    2610.02741
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Ouro-1.4B-Thinking, Ouro-2.6B-Thinking, Nanbeige4.2-3B and others4
    Abstract加深 loop 可在部分压力测试任务降低可监测性，循环架构本身并不必然更难监测。

    这项工作评估 LoopLM 的 CoT 可监测性：加深共享层的重复次数，以及“有循环结构”本身，会不会让决策关键因素更少出现在可监测文本里。

    Paper analysisRead analysis
  2. Analysis and theoryarXiv 2609.37312

    研究：隐蔽推理必然留下信息痕迹，但思维链未必可读

    分析隐蔽推理在思维链监控下的信息足迹下界与不可读性

    arXiv
    2609.37312
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Qwen 3.5 397B-A17B and others12

    Abstract论文从理论与实证探明了思维链监控的边界：复杂隐蔽计算必然泄露信息足迹且需承担长度税，但该足迹可被在线加密而不可读。

    Paper analysisRead analysis
You have reached the end