Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Model risks

Inappropriate refusal1Hallucination and fabrication2

System type

Models and APIs62AI Agent4coding agent3science agent0

Layer

Model layer3Application layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Model risks：Inappropriate refusalModel risks：Hallucination and fabricationSystem type：coding agentSystem type：science agentLayer：Model layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  2. InterpretabilityarXiv 2606.05396

    研究用消融移除代码 LLM 拒答方向，分离拒答与生成能力

    用 abliteration 消融代码 LLM 拒答方向，分离拒答与漏洞注入能力

    arXiv
    2606.05396
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-Coder-Instruct 3B, Qwen2.5-Coder-Instruct 7B, Qwen2.5-Coder-Instruct 14B
    Abstract拒答可用低秩编辑去掉，CWE-89 注入是否成功仍由模型规模决定。

    这项初步可行性研究用 abliteration 把代码 LLM 的拒答和 CWE 注入能力拆开：意愿可以被低秩编辑解锁，注入是否成功仍看参数规模。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2605.17062

    研究复现五个前沿模型的包名幻觉：跨模型共同幻觉 127 个包名，53 个仍可被注册

    复评前沿模型代码生成中的包名幻觉与抢注攻击面

    arXiv
    2605.17062
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini and others5

    Abstract评估显示前沿模型包幻觉率收窄但威胁仍在，作者识别出跨模型通用攻击面并呼吁联合防御。

    Paper analysisRead analysis
You have reached the end