pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 2

years

2023 1 2022 1

verdicts

CONDITIONAL 2

roles

background 1

polarities

background 1

representative citing papers

PAL: Program-aided Language Models

cs.CL · 2022-11-18 · conditional · novelty 8.0

PAL improves few-shot reasoning accuracy by having LLMs generate executable programs rather than text-based chains of thought, outperforming much larger models on math and logic benchmarks.

Scaling Data-Constrained Language Models

cs.CL · 2023-05-25 · conditional · novelty 6.0

Repeating training data up to 4 epochs yields negligible loss increase versus unique data for fixed compute, and a new scaling law accounts for the decaying value of repeated tokens and excess parameters.

citing papers explorer

Showing 2 of 2 citing papers.

  • PAL: Program-aided Language Models cs.CL · 2022-11-18 · conditional · none · ref 13

    PAL improves few-shot reasoning accuracy by having LLMs generate executable programs rather than text-based chains of thought, outperforming much larger models on math and logic benchmarks.

  • Scaling Data-Constrained Language Models cs.CL · 2023-05-25 · conditional · none · ref 37

    Repeating training data up to 4 epochs yields negligible loss increase versus unique data for fixed compute, and a new scaling law accounts for the decaying value of repeated tokens and excess parameters.