物界前沿 · 资讯情报卡(HuggingFace · 2026/11/4)

StateBench: Testing how language models track state changes over long documents

# StateBench: Testing how language models track state changes over long documents ![Ai2's avatar](https://cdn-avatars.huggingface.co/v1/production/up

这条资讯的完整报道在HuggingFace站点

物界前沿暂未生成该篇情报卡(来源受限或排队提炼中),点击下方按钮阅读原文。

阅读原文 ↗
本页内容为简要索引,详细报道请点击原文查看。

来源:HuggingFace原文 ↗