Intrinsic Entropy of Context Length Scaling in LLMs

ICLR 2026 Conference Submission9559 Authors

Keywords: context length, intrinsic entropy

TL;DR: We propose to use Intrinsic Entropy for understanding impact of context length on Language Modeling, and conduct experiments to validate theoretical assumptions and deductions with language and synthetic datasets.

Abstract: There has been work discussing the impact of long context on Language Model performance: some find that long irrelevant context could harm performance, while some experimentally summarize loss reduction by relevant long context as Scaling Laws. This calls for a more thorough understanding on how long context impacts Language Modeling. In this work, we (1) propose to use Intrinsic Entropy for explaining the impact of context length on language modeling; and (2) conduct experiments on natural language and synthetic data, validating our proposed theoretical assumptions and deductions. Our theoretical framework can provide practical insights such as establishing that training dataset size dictates an optimal context length and bounds context length scaling for certain cases. We hope our work may inspire new long context Language Models, as well as future work studying Physics for Language Models.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 9559