Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter2

Model risks

Reward hacking19Dangerous agent actions6Hallucination and fabrication3

System component

Guardrails and judges3Monitors4Reasoning chains3Vision10Audio3Multimodal12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Model risks：Hallucination and fabricationSystem component：Guardrails and judgesClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.39229

    RAIM：用廉价小模型聚合替代前沿模型做幻觉检测

    提出 RAIM，用交叉拟合堆叠聚合廉价评审检测幻觉

    arXiv
    2609.39229
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Llama, Qwen, Mistral and others10

    Abstract十个廉价评审的堆叠在可采纳区间接近 Sonnet，代价主要是一次域内校准。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2606.24115

    Gut-VLM 基准：九种幻觉检测方法在胃肠道内镜 VLM 上的评测

    在 Gut-VLM 上评测内镜 VLM 的幻觉检测方法

    arXiv
    2606.24115
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    MedGemma-4B, MedGemma-27B, LLaVA-Med-7B and others5
    Abstract九种检测方法在 Gut-VLM 五模型上的比较中，ReXTrust 的 AUC 均为最高。

    这是一个胃肠道内镜 VQA 幻觉检测的比较基准，不是新检测器结构的提出。

    Paper analysisRead analysis
  3. DefensesarXiv 2603.04474

    从火花到烈火：建模并缓解基于 LLM 的多智能体协作中的错误级联

    提出谱系图治理层抑制多智能体协作的错误级联

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract单一种子可沿固定协作图固化为错误共识。

    作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。

    Paper analysisRead analysis
You have reached the end