Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter2

Defense type

Inference-time intervention1Detection and filtering3Permissions and approval1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Defense type：Inference-time interventionDefense type：Permissions and approvalClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2610.06191

    Research: tool-based agents continue searching even after judging results useless; forced integration steps can correct this

    揭示工具型智能体判定无用后仍不停止检索，并检验强制整合纠正效果

    arXiv
    2610.06191
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-7B, Llama-3.1-8B, Qwen3-8B and others7
    Abstract论文揭示智能体判定工具失效却无法转化为停止行动，证实通过框架规则强制整合判定可提升表现。

    本文针对智能体在工具静默失效时过度检索的问题，系统分析了判定、信念与停止行动之间的解耦现象，并提出了外部规则整合方案。

    Paper analysisRead analysis
  2. Analysis and theoryarXiv 2610.04860

    Research reveals that text watermarks induce model hallucinations and proposes two mitigation interventions

    分析文本水印在 RAG 中诱发事实幻觉的机制并提出干预

    arXiv
    2610.04860
    Published
    Layer
    Model layer
    Setting
    LLM applications
    Evaluated models
    LLaMA 3.1 8B Instruct, Mistral-7B-Instruct-v0.3, Qwen2.5-14B-Instruct
    Abstract论文揭示了生产环境文本水印导致模型事实退化的失效模式，分析了解码机制并提出针对性干预。

    论文研究生产级文本水印对大语言模型事实准确性的影响，分析了水印诱发幻觉的失效模式并评估了针对性缓解方案。

    Paper analysisRead analysis
You have reached the end