Logo image
Slaves to the Law of Large Numbers: An Asymptotic Equipartition Property for Perplexity in Generative Language Models
Preprint   Open access

Slaves to the Law of Large Numbers: An Asymptotic Equipartition Property for Perplexity in Generative Language Models

Raghu Mudumbai and Tyler Bell
arXiv.org
Cornell University
05/22/2024
DOI: 10.48550/arxiv.2405.13798
url
https://doi.org/10.48550/arxiv.2405.13798View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

We propose a new asymptotic equipartition property for the perplexity of a large piece of text generated by a language model and present theoretical arguments for this property. Perplexity, defined as a inverse likelihood function, is widely used as a performance metric for training language models. Our main result states that the logarithmic perplexity of any large text produced by a language model must asymptotically converge to the average entropy of its token distributions. This means that language models are constrained to only produce outputs from a ``typical set", which we show, is a vanishingly small subset of all possible grammatically correct outputs. We present preliminary experimental results from an open-source language model to support our theoretical claims. This work has possible practical applications for understanding and improving ``AI detection" tools and theoretical implications for the uniqueness, predictability and creative potential of generative models.
Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Information Theory Mathematics - Information Theory

Details

Metrics

15 Record Views
Logo image