Phase transition on a context-sensitive random language model with short range interactions
This clarifies a foundational issue in statistical mechanics applied to language models, showing phase transitions are not merely artifacts of long-range interactions.
The authors tackled the problem of whether phase transitions in language models arise from linguistic properties or long-range interactions by constructing a random language model with short-range interactions and context-sensitive grammars. They found that a phase transition occurs even with constant-length contexts, indicating it is intrinsic to language.
Since the random language model was proposed by E. DeGiuli [Phys. Rev. Lett. 122, 128301], language models have been investigated intensively from the viewpoint of statistical mechanics. Recently, the existence of a Berezinskii--Kosterlitz--Thouless transition was numerically demonstrated in models with long-range interactions between symbols. In statistical mechanics, it has long been known that long-range interactions can induce phase transitions. Therefore, it has remained unclear whether phase transitions observed in language models originate from genuinely linguistic properties that are absent in conventional spin models. In this study, we construct a random language model with short-range interactions and numerically investigate its statistical properties. Our model belongs to the class of context-sensitive grammars in the Chomsky hierarchy and allows explicit reference to contexts. We find that a phase transition occurs even when the model refers only to contexts whose length remains constant with respect to the sentence length. This result indicates that finite-temperature phase transitions in language models are genuinely induced by the intrinsic nature of language, rather than by long-range interactions.