Readability ≠ Learnability: Rethinking the Role of Simplicity in Training Small Language Models

Ivan Lee, Taylor Berg-Kirkpatrick

Keywords: child-directed language, developmentally inspired data, small language models

TL;DR: This paper argues statistical simplicity (low n-gram diversity), not human readability, is the critical factor enabling coherence emergence in small language models trained on synthetic datasets like TinyStories.

Abstract: Recent studies suggest that very small language models (SLMs) can generate surprisingly coherent text when trained on simplified, child-directed corpora such as TinyStories. These findings have been interpreted as evidence that readability—characterized by accessible vocabulary, familiar narrative structure, and simple syntax—plays a key role in enabling such capabilities to emerge. In this paper, we challenge that interpretation. We construct synthetic datasets with matched structure but varied readability, and find that readability alone does not predict coherence or learning efficiency in SLMs. Models trained on complex, adult-level text perform comparably to those trained on simplified language, and even exhibit faster development of coherence during training. Instead, we show that statistical simplicity, as measured by n-gram diversity, is a stronger predictor of learnability. Our findings caution against the growing trend of anthropomorphizing language model training—drawing parallels to human cognitive development without empirical basis—and argue for more precise reasoning about what properties actually support capability emergence in small models.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Award Nomination: true

Submission Number: 1813