Pith. sign in

Data-efficient adaptation of multilingual LLMs to Ukrainian

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

ACCEPT 1

representative citing papers

Writing-System-Level Tokenizer Adaptation for Byte-Level BPE

cs.CL · 2026-08-01 · accept · novelty 6.0

A fixed-vocabulary tokenizer surgery method reduces Ukrainian token counts by 33-37% on Nemotron and GPT-OSS while preserving 77-78% of original token IDs and leaving English and EU token counts essentially unchanged.

citing papers explorer

Showing 1 of 1 citing paper.

  • Writing-System-Level Tokenizer Adaptation for Byte-Level BPE cs.CL · 2026-08-01 · accept · none · ref 9

    A fixed-vocabulary tokenizer surgery method reduces Ukrainian token counts by 33-37% on Nemotron and GPT-OSS while preserving 77-78% of original token IDs and leaving English and EU token counts essentially unchanged.