Fractal Patterns May Illuminate the Success of Next-Token Prediction
Keywords: fractal patterns, large language models, Hurst exponent, self-similarity, Joseph exponent, perplexity, information theory
TL;DR: We study the fractal structure of language and show that fractal parameter can be used in predicting downstream performance better than perplexity-based metrics alone.
Abstract: We study the fractal structure of language, aiming to provide a precise formalism for quantifying properties that may have been previously suspected but not formally shown. We establish that language is: (1) self-similar, exhibiting complexities at all levels of granularity, with no particular characteristic context length, and (2) long-range dependent (LRD), with a Hurst parameter of approximately 0.7.
Based on these findings, we argue that short-term patterns/dependencies in language, such as in paragraphs, mirror the patterns/dependencies over larger scopes, like entire documents. This may shed some light on how next-token prediction can capture the structure of text across multiple levels of granularity, from words and clauses to broader contexts and intents. In addition, we carry out an extensive analysis across different domains and architectures, showing that fractal parameters are robust.
Finally, we demonstrate that the tiny variations in fractal parameters seen across LLMs improve upon perplexity-based bits-per-byte (BPB) in predicting their downstream performance. We hope these findings offer a fresh perspective on language and the mechanisms underlying the success of LLMs.
Primary Area: Natural language processing
Submission Number: 4781
Loading