跳到正文
稳定技术报道时间 2026-10-02 12:00

Halluscoring 2026:首个大型语言模型幻觉检测共享任务

一个新的共享任务HalluScoring 2026被引入,用于评估阿拉伯语问答中的幻觉检测和事实验证,重点关注对未见过的问题和大语言模型的泛化能力。

01

证据

  • AarXiv cs.CL研究机构2026-10-02 12:00
    > Abstract: We present HalluScoring 2026, a shared task for evaluating hallucination detection and factual verification in Arabic question answering under chal…
    查看来源
  • AarXiv cs.CL研究机构2026-10-02 12:00
    Abstract: We present HalluScoring 2026, a shared task for evaluating hallucination detection and factual verification in Arabic question answering under challe…
    查看来源