Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper, we investigate whether the same happens if artificial languages are optimised for implicit biases of Large Language Models (LLMs). To this end, we simulate a classical referential game in which LLMs learn and use artificial languages. Our results show that initially unstructured holistic languages are indeed shaped to have some structural properties that allow two LLM agents to communicate successfully. Similar to observations in human experiments, generational transmission increases the learnability of languages, but can at the same time result in non-humanlike degenerate vocabularies. Taken together, this work extends experimental findings, shows that LLMs can be used as tools in simulations of language evolution, and opens possibilities for future human-machine experiments in this field.

翻译：人类语言通过反复的语言学习与使用过程演化出结构。这些过程引入了在语言习得期间起作用的偏见，并将语言系统塑造成具有交际效率的形式。本文研究若人工语言针对大语言模型（LLMs）的隐式偏见进行优化，是否会产生相同结果。为此，我们模拟了一个经典的指称游戏，让LLMs在其中学习并使用人工语言。实验结果表明：最初无结构的整体语言确实会被塑造成具有某些结构特性，使得两个LLM智能体能够成功通信。与人类实验观察相似，代际传递提升了语言的可学习性，但同时也可能导致非人类式的退化词汇表。综上所述，本研究拓展了实验发现，证明LLMs可作为语言演化模拟的研究工具，并为该领域未来的人机实验开辟了可能性。