LLMs can compose surface-form tokens from base embeddings plus learned transformation vectors, freeing 10-40% of vocabulary slots while expanding coverage and preserving downstream performance across five languages.
InProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 18761–18799, Vienna, Austria
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic
LLMs can compose surface-form tokens from base embeddings plus learned transformation vectors, freeing 10-40% of vocabulary slots while expanding coverage and preserving downstream performance across five languages.