Token pruning of non-Korean vocabulary in LLMs improves generation stability and often boosts machine translation on Korean tasks while cutting vocabulary size substantially.
InFindings of the Association for Computational Linguistics: ACL 2025, pages 12257–12284
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimizing Korean-Centric LLMs via Token Pruning
Token pruning of non-Korean vocabulary in LLMs improves generation stability and often boosts machine translation on Korean tasks while cutting vocabulary size substantially.