Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Logits-Based Finetuning

cs.LG · 2025-05-30 · conditional · novelty 5.0

The proposed logits-based fine-tuning, which mixes teacher logits with ground truth labels, improves math reasoning accuracy of small LLaMA models over standard supervised fine-tuning, with a controlled GSM8K gain of 2.0 points and larger claimed gains on other benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Logits-Based Finetuning cs.LG · 2025-05-30 · conditional · none · ref 4

    The proposed logits-based fine-tuning, which mixes teacher logits with ground truth labels, improves math reasoning accuracy of small LLaMA models over standard supervised fine-tuning, with a controlled GSM8K gain of 2.0 points and larger claimed gains on other benchmarks.