AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives

Ander Artola Velasco, Stratis Tsirtsis, Nastaran Okati, Manuel Gomez Rodriguez

ICML 2026 · Large language models › Language, safety and interpretability · approach: LLM unlearning and benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase top-p from 0.90 to 0.99token-splitting heuristic, Llama-3.2-1B-Instruct · LMSYS T=1.3max % tokens overcharged: 0.28 -> 11.2Improved
raise number of splitting iterations m beyond optimumtoken-splitting heuristic · LMSYS T=1.3additional revenueHurt
increase sampling temperaturetoken-splitting heuristic · LMSYSfraction of outputs with longer plausible tokenizationImproved
raise top-p from 0.90 to 0.99misreporting provider · LMSYS T=1.3provider utility gain: 0.4 -> 10.5Improved
lower provider profit marginmisreporting provider · LMSYS T=1.3relative utility gainImproved
switch from pay-per-token to pay-per-character with r_c = r_o*tpcprovider profit margin · LMSYS T=1.3 p=0.95average profit margin: 92.4%, 93.3%, 94.1% positive marginNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy