LLMs syntactically adapt their language use to their conversational partner

Florian Kandra, Vera Demberg, Alexander Koller
3/10/2025
cs.CL

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Do language models accommodate their users? A study of linguistic convergence

88% match2025

Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs

88% match1 repo52024

Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication

86% match2025

Mind the Gap: Linguistic Divergence and Adaptation Strategies in Human-LLM Assistant vs. Human-Human Interactions

85% match2025

Do Large Language Models Adapt to Language Variation across Socioeconomic Status?

84% match2026

Are Human Conversations Special? A Large Language Model Perspective

84% match2024

Cite this paper

@article{kandra2025llms,
  title  = {LLMs syntactically adapt their language use to their conversational partner},
  author = {Florian Kandra and Vera Demberg and Alexander Koller},
  year   = {2025},
  eprint = {2503.07457},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.07457v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.07457.svg)](https://codeofpaper.com/paper/2503.07457)

Discussion