LLMs exhibit the Position Curse, with backward position retrieval in lists lagging far behind forward retrieval, showing only partial gains from PosBench fine-tuning.
The strawberry problem: Emergence of character-level understanding in tokenized language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
citing papers explorer
-
The Position Curse: LLMs Struggle to Locate the Last Few Items in a List
LLMs exhibit the Position Curse, with backward position retrieval in lists lagging far behind forward retrieval, showing only partial gains from PosBench fine-tuning.
-
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.