mlsanityData to 14 Oct 2026

LLMs syntactically adapt their language use to their conversational partner

arXiv 2503.07457 ↗First posted 10 Mar 2025cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 9 of its 38 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

9 of 38 references.

References · 9

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 839
  3. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 629
  4. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  5. 2018Constituency Parsing with a Self-Attentive Encodercited by 199
  6. 2018Multilingual Constituency Parsing with Self-Attention and Pre-Trainingcited by 117
  7. 2023Do large language models resemble humans in language use?cited by 34
  8. 2022Norm Participation Grounds Languagecited by 4
  9. 2024Fine-grained Controllable Text Generation through In-context Learning with Feedbackcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 9.

15 papers.

Sort:

  1. 2025Do language models accommodate their users? A study of linguistic convergencecited by 7
  2. 2025A Review of Incorporating Psychological Theories in LLMscited by 6
  3. 2026Markovian Generation Chains in Large Language Modelscited by 3
  4. 2026Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Modelscited by 2
  5. 2025Language models as tools for investigating the distinction between possible and impossible natural languagescited by 0
  6. 2025Large language models have learned to use languagecited by 0
  7. 2025Large language models are not about natural languagecited by 0
  8. 2025Linguists should learn to love speech-based deep learning modelscited by 0
  9. 2026Are Language Models Models?cited by 0
  10. 2026Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventionscited by 0
  11. 2026Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilitiescited by 0
  12. 2026You Can't Fight in Here! This is BBS!cited by 0
3 more
  1. 2026Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appearcited by 0
  2. 2026Defeat Devices in AI Systemscited by 0
  3. 2026Instruction-Tuned Models Locally Reuse Human Syntax More Than Humans Docited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs
  2. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
  3. 2025Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History
  4. 2024Beware of Words: Evaluating the Lexical Diversity of Conversational LLMs using ChatGPT as Case Study
  5. 2025Can LLM Agents Maintain a Persona in Discourse?
  6. 2024Examining Identity Drift in Conversations of LLM Agents
  7. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey
  8. 2026"Who Am I, and Who Else Is Here?" Behavioral Differentiation Without Role Assignment in Multi-Agent LLM Systems