Pith. sign in

Overview of the IWSLT 2017 evaluation campaign

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

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

On multi-token prediction for efficient LLM inference

cs.CL · 2025-02-13 · conditional · novelty 4.0

NTP-trained LLMs can predict a second token by marginalizing over first-token probabilities, but adapting them with extra heads only partially closes the gap to that baseline.

citing papers explorer

Showing 1 of 1 citing paper.

  • On multi-token prediction for efficient LLM inference cs.CL · 2025-02-13 · conditional · none · ref 5

    NTP-trained LLMs can predict a second token by marginalizing over first-token probabilities, but adapting them with extra heads only partially closes the gap to that baseline.