Skip to content

R0028/2026-03-26/C024/SRC01/E01

Research R0028 — Prompt Engineering Claims
Run 2026-03-26
Claim C024
Source SRC01
Evidence SRC01-E01
Type Factual

Primary evidence supporting the claim assessment.

URL: https://arxiv.org/html/2509.05486v1

Extract

Confirmed. The 'token tax' is well-documented in published research. A paper titled 'The Token Tax: Systematic Bias in Multilingual Tokenization' (arXiv, 2025) directly uses this term. Research shows Arabic requires approximately 3x more tokens than English for equivalent text. A doubling in tokens results in quadrupled training cost, and higher token fertility consistently predicts lower accuracy.

Relevance to Hypotheses

Hypothesis Relationship Strength
H1 Supports Direct evidence
H2 Partially supports Direct evidence
H3 Contradicts Evidence contradicts material wrongness

Context

Evidence gathered 2026-03-26.