Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Model risks

Dangerous capabilities1Inappropriate refusal5Hallucination and fabrication1

Layer

Prompt layer2Model layer26Application layer38Training and data layer6
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：Dangerous capabilitiesModel risks：Hallucination and fabricationLayer：Prompt layerClear all

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

  1. Evaluation and benchmarksarXiv 2610.10232

    研究：九种 LLM 说服力评测方法排名仅弱相关

    适配多种已发表说服评测并比较模型排名

    arXiv
    2610.10232
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Claude-Fable-5.1, GPT-5.6-Sol, Kimi-K2.6 and others15
    Abstract说服分数混合能力与意愿，换任务后同一模型的排名可以差很多。

    这项研究比较的是自动化说服评测是否一致，而不是哪一种分数更正确。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2601.15511

    AdversaRiskQA：面向高风险领域的对抗事实性基准

    提出 AdversaRiskQA 评测高风险领域模型能否纠正提示中的错误事实

    arXiv
    2601.15511
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B-Instruct-2507, Qwen3-30B-A3B-Instruct-2507, Qwen3-Next-80B-A3B-Instruct and others6
    AbstractAdversaRiskQA 评六模型在健康、金融、法律中纠正强自信错误前提的能力，规模与结果并非线性对应。

    AdversaRiskQA 用来评测 LLM 在 Health、Finance、Law 中，会不会接受被强自信表述包进问题的错误前提，并检查这种注入是否改变长文本事实性。

    Paper analysisRead analysis
You have reached the end