CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
The strawberry problem: Emergence of character-level understanding in tokenized language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
LLMs exhibit the Position Curse, with backward position retrieval in lists lagging far behind forward retrieval, showing only partial gains from PosBench fine-tuning.
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
citing papers explorer
-
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.