Scale-Dependent Semantic Dynamics Revealed by Allan Deviation
This work addresses the challenge of quantifying semantic dynamics in language for researchers in computational linguistics and AI, offering a framework to distinguish human cognition from algorithmic patterns, though it is incremental in applying existing metrology tools to this domain.
The researchers tackled the problem of understanding semantic progression in written text by analyzing it as a stochastic trajectory using Allan deviation, revealing two dynamical regimes that differentiate creative literature from technical texts and showing that large language models mimic local scaling but have reduced stability horizons.
While language progresses through a sequence of semantic states, the underlying dynamics of this progression remain elusive. Here, we treat the semantic progression of written text as a stochastic trajectory in a high-dimensional state space. We utilize Allan deviation, a tool from precision metrology, to analyze the stability of meaning by treating ordered sentence embeddings as a displacement signal. Our analysis reveals two distinct dynamical regimes: short-time power-law scaling, which differentiates creative literature from technical texts, and a long-time crossover to a stability-limited noise floor. We find that while large language models successfully mimic the local scaling statistics of human text, they exhibit a systematic reduction in their stability horizon. These results establish semantic coherence as a measurable physical property, offering a framework to differentiate the nuanced dynamics of human cognition from the patterns generated by algorithmic models.