Pith. sign in

Tokenisation is NP-Complete

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

1 Pith paper citing it
abstract

In this work, we prove the NP-completeness of two variants of tokenisation, defined as the problem of compressing a dataset to at most $\delta$ symbols by either finding a vocabulary directly (direct tokenisation), or selecting a sequence of merge operations (bottom-up tokenisation).

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Causal Estimation of Tokenisation Bias

cs.CL · 2025-06-03 · conditional · novelty 7.0

Using regression discontinuity, the paper shows that adding a subword to a tokenizer's vocabulary can raise the model's probability for that string by up to about 17 times in small models.

citing papers explorer

Showing 1 of 1 citing paper.

  • Causal Estimation of Tokenisation Bias cs.CL · 2025-06-03 · conditional · none · ref 47 · internal anchor

    Using regression discontinuity, the paper shows that adding a subword to a tokenizer's vocabulary can raise the model's probability for that string by up to about 17 times in small models.