English

Applying SoftTriple Loss for Supervised Language Model Fine Tuning

Computation and Language 2022-11-28 v1

Abstract

We introduce a new loss function TripleEntropy, to improve classification performance for fine-tuning general knowledge pre-trained language models based on cross-entropy and SoftTriple loss. This loss function can improve the robust RoBERTa baseline model fine-tuned with cross-entropy loss by about (0.02% - 2.29%). Thorough tests on popular datasets indicate a steady gain. The fewer samples in the training dataset, the higher gain -- thus, for small-sized dataset it is 0.78%, for medium-sized -- 0.86% for large -- 0.20% and for extra-large 0.04%.

Cite

@article{arxiv.2112.08462,
  title  = {Applying SoftTriple Loss for Supervised Language Model Fine Tuning},
  author = {Witold Sosnowski and Anna Wroblewska and Piotr Gawrysiak},
  journal= {arXiv preprint arXiv:2112.08462},
  year   = {2022}
}
R2 v1 2026-06-24T08:19:18.468Z