ACL 2025short0 citations
LLMs syntactically adapt their language use to their conversational partner
Florian Kandra, Vera Demberg, Alexander Koller
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 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.
BibTeX
@inproceedings{kandra-etal-2025-llms,
title = "{LLM}s syntactically adapt their language use to their conversational partner",
author = "Kandra, Florian and
Demberg, Vera and
Koller, Alexander",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-short.68/",
doi = "10.18653/v1/2025.acl-short.68",
pages = "873--886",
ISBN = "979-8-89176-252-7"
}