English

Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models

Computation and Language 2026-05-29 v1

Abstract

As LLMs become increasingly integrated into daily life, understanding how their presence will shape human linguistic behavior is an open question. We present a large-scale study of linguistic convergence in human-LLM dialogue, examining how humans and LLMs accommodate each other's linguistic style during multi-turn conversations. Using an asymmetric convergence metric on WildChat, a corpus of real-world ChatGPT transcripts, we find that while LLMs significantly overconverge toward their users on both function word and open-class features across eight languages, human convergence rates in this setting are broadly consistent with human-human baselines. These findings suggest that accommodation in human-LLM dialogue is asymmetric: while LLMs dramatically overfit to their users' style, humans linguistically accommodate LLMs no differently than they would another person.

Keywords

Cite

@article{arxiv.2605.29278,
  title  = {Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models},
  author = {Terra Blevins},
  journal= {arXiv preprint arXiv:2605.29278},
  year   = {2026}
}
R2 v1 2026-07-22T07:38:34.258Z