English

States of LLM-generated Texts and Phase Transitions between them

Computation and Language 2025-03-11 v1 Statistical Mechanics Artificial Intelligence

Abstract

It is known for some time that autocorrelations of words in human-written texts decay according to a power law. Recent works have also shown that the autocorrelations decay in texts generated by LLMs is qualitatively different from the literary texts. Solid state physics tie the autocorrelations decay laws to the states of matter. In this work, we empirically demonstrate that, depending on the temperature parameter, LLMs can generate text that can be classified as solid, critical state or gas.

Keywords

Cite

@article{arxiv.2503.06330,
  title  = {States of LLM-generated Texts and Phase Transitions between them},
  author = {Nikolay Mikhaylovskiy},
  journal= {arXiv preprint arXiv:2503.06330},
  year   = {2025}
}

Comments

Published as a conference paper at MathAI 2025