一篇新的研究论文调查了大型语言模型（LLMs）在理解中文零代词方面的能力，零代词是主语省略语言中常见的语言特征。研究发现，尽管大型语言模型在中文任务方面普遍熟练，但它们在零代词方面却面临着重大挑战，尤其是在识别和分类方面。即使是先进的推理模型，将这些代词正确翻译成英语的比例也不到一半，这表明当前的大型语言模型技术面临着严峻的挑战。 AI
影响 突出了大型语言模型面临的特定语言挑战，为未来模型的开发和评估指明了方向。
排序理由 该集群包含一篇详细介绍大型语言模型能力研究结果的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.31056v1 Announce Type: new Abstract: Zero Pronouns (ZPs) are a pervasive linguistic phenomenon in pro-drop languages such as Chinese and have long posed a challenge for natural language processing systems. Although Large Language Models (LLMs) perform well on many Chin…
Zero Pronouns (ZPs) are a pervasive linguistic phenomenon in pro-drop languages such as Chinese and have long posed a challenge for natural language processing systems. Although Large Language Models (LLMs) perform well on many Chinese language tasks, their ability to process ZPs…