Rethinking the Role of Text Complexity in Language Model Pretraining
By: Dan John Velasco, Matthew Theodore Roque
Potential Business Impact:
Makes AI understand easier text better.
Improving pretraining data quality and size is known to boost downstream performance, but the role of text complexity is less explored. Text complexity refers to how hard a text is to read, and is typically estimated from surface cues such as sentence length, word choice, and sentence structure. We reduce surface-level complexity--shorter sentences, simpler words, simpler structure--while keeping core text content close to constant, and ask: (1) How does complexity affect language modeling across model sizes? (2) Can useful representations be learned from simpler text alone? (3) How does pretraining text complexity influence downstream language understanding? To answer these questions, we simplify human-written texts using a large language model, then pretrain causal models (28M-500M) from scratch on both original and simplified data, and evaluate them in finetuning and zero-shot setups. We find that perplexity is sensitive to the interaction between model capacity and text complexity--smaller models degrade far less on simpler texts--while text complexity has little impact on finetuning evaluations, with zero-shot evaluations indicating that simpler texts benefit performance on linguistic knowledge tasks, whereas more complex texts favor tasks requiring world knowledge and entity tracking.
Similar Papers
Readability $\ne$ Learnability: Rethinking the Role of Simplicity in Training Small Language Models
Computation and Language
Simple words don't always make computers learn better.
Scaling, Simplification, and Adaptation: Lessons from Pretraining on Machine-Translated Text
Computation and Language
Helps computers learn many languages with less text.
Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions
Computation and Language
Smart computer programs learn better with smarter building.