BriefGPT.xyz
Mar, 2025
大语言模型如何在对话中语法适应其交谈伙伴
LLMs syntactically adapt their language use to their conversational partner
HTML
PDF
Florian Kandra, Vera Demberg, Alexander Koller
TL;DR
本研究探讨了大型语言模型（LLMs）在对话中是否表现出与人类类似的语言适应行为。通过构建对话语料库，发现LLMs在交流中随着对话的进行其语法选择逐渐趋同，表明现代LLMs在某种程度上能够适应其对话伙伴的语言使用。这一发现为理解和提升LLMs的对话能力提供了重要见解。
Abstract
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
Co
→