Pith. sign in

Title resolution pending

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 Support Samples of Next Word Prediction

cs.CL · 2025-06-04 · conditional · novelty 6.0

Training examples that most shape a GPT-2 model's next-word predictions can be identified with about 80% accuracy from the randomly initialized model, before any training.

citing papers explorer

Showing 1 of 1 citing paper.

  • On Support Samples of Next Word Prediction cs.CL · 2025-06-04 · conditional · none · ref 6

    Training examples that most shape a GPT-2 model's next-word predictions can be identified with about 80% accuracy from the randomly initialized model, before any training.