Export citation

Export citation

Choose format for download:

Download Citation

    Berezinskii-Kosterlitz-Thouless transition in a context-sensitive random language model

    Yuma Toji1, Jun Takahashi2, Vwani Roychowdhury3, and Hideyuki Miyahara1,*

    • 1Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Hokkaido 060-0814, Japan
    • 2Institute for Solid State Physics, The University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa, Chiba 277-8581, Japan
    • 3Henry Samueli School of Engineering and Applied Science, University of California, Los Angeles, California 90095, USA

    • *Contact author: miyahara@ist.hokudai.ac.jp: hmiyahara512@gmail.com

    Phys. Rev. E 113, 015305 – Published 21 January, 2026

    DOI: https://doi.org/10.1103/s7nf-bwzd

    Abstract

    Several power-law critical properties involving different statistics in natural languages—reminiscent of scaling properties of physical systems at or near phase transitions—have been documented for decades. The recent rise of large language models has added further evidence and excitement by providing intriguing similarities with notions in physics such as scaling laws and emergent abilities. However, specific instances of classes of generative language models that exhibit phase transitions, as understood by the statistical physics community, are lacking. In this work, inspired by the one-dimensional Potts model in statistical physics, we construct a simple probabilistic language model that falls under the class of context-sensitive grammars, which we call the context-sensitive random language model, and numerically demonstrate an unambiguous phase transition in the framework of a natural language model. We explicitly show that a precisely defined order parameter—that captures symbol frequency biases in the sentences generated by the language model—changes from strictly zero to a strictly nonzero value (in the infinite-length limit of sentences), implying a mathematical singularity arising when tuning the parameter of the stochastic language model we consider. Furthermore, we identify the phase transition as a variant of the Berezinskii–Kosterlitz–Thouless (BKT) transition, which is known to exhibit critical properties not only at the transition point but also in the entire phase. This finding leads to the possibility that critical properties in natural languages may not require careful fine-tuning nor self-organized criticality, but are generically explained by the underlying connection between language structures and the BKT phases. From a statistical physics perspective, our paper captures a rare phenomenon of the BKT phase in a one-dimensional system, as the BKT phase is widely studied and believed to exist only in two-dimensional systems.

    Physics Subject Headings (PhySH)

    Authorization Required

    We need you to provide your credentials before accessing this content.

    References (Subscription Required)

    Outline

    Information

    Sign In to Your Journals Account

    Filter

    Filter

    Article Lookup

    Enter a citation