大模型已学会用语言，突破传统语言认知研究范式。

Large language models have learned to use language

• 承认大模型掌握语言使用，挑战传统语言评估标准
• 进入后图灵测试时代，需重新审视语言智能本质
• 为语言科学带来新范式，适合关注AI与语言交叉的学者

承认大语言模型已学会使用语言，可能为语言科学带来突破性进展。实现这些突破，可能需要摒弃一些长期坚持的语言知识评估理念，并正视我们已进入后图灵测试时代的现实。

原文摘要 · Abstract (English)

Acknowledging that large language models have learned to use language can open doors to breakthrough language science. Achieving these breakthroughs may require abandoning some long-held ideas about how language knowledge is evaluated and reckoning with the difficult fact that we have entered a post-Turing test era.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。