大模型会随对话伙伴调整语法风格，表现出语言适应性。
LLMs syntactically adapt their language use to their conversational partner
- 通过构建双大模型对话数据集，观察语法选择趋同
- 对话越深入，双方句式结构越相似，表明存在适应行为
- 适合关注大模型社交交互能力的研究者阅读
已有大量观察表明，人类在对话中会相互调整语言使用。本文首次从实证角度研究大型语言模型（LLMs）是否具备类似的语言适应行为。我们构建了一个由两个大模型代理进行对话的语料库，发现随着对话进行，两者在句法选择上趋于一致，证实现代大模型至少以一种初步方式能够根据对话伙伴调整自身语言风格。
原文摘要 · Abstract (English)
It has been frequently observed that human speakers align their language use with each other during conversations. In this paper, we study empirically whether large language models (LLMs) exhibit the same behavior of conversational adaptation. We construct a corpus of conversations between LLMs and find that two LLM agents end up making more similar syntactic choices as conversations go on, confirming that modern LLMs adapt their language use to their conversational partners in at least a rudimentary way.
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。