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

TL;DR

This paper introduces a simple probabilistic language model inspired by the Potts model, demonstrating a Berezinskii--Kosterlitz--Thouless phase transition in language structure, revealing potential universal critical properties in natural languages.

Contribution

It constructs a context-sensitive probabilistic language model that exhibits a BKT phase transition, linking language phenomena to statistical physics concepts.

Findings

Identifies a phase transition in a language model via an order parameter.

Shows the transition is of BKT type with critical properties across phases.

Suggests natural language criticality may stem from underlying physics principles.

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.