Pith. sign in

Language model tokenizers introduce unfairness between languages

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

SpeLLM: Character-Level Multi-Head Decoding

cs.CL · 2025-07-22 · conditional · novelty 6.0

SpeLLM converts a standard token-based LLM into a character-spelling model with multiple parallel output heads, achieving competitive downstream performance with a 5.1% average decoding speedup.

citing papers explorer

Showing 1 of 1 citing paper.

  • SpeLLM: Character-Level Multi-Head Decoding cs.CL · 2025-07-22 · conditional · none · ref 7

    SpeLLM converts a standard token-based LLM into a character-spelling model with multiple parallel output heads, achieving competitive downstream performance with a 5.1% average decoding speedup.