English

Parameter-Efficient Tuning with Special Token Adaptation

Computation and Language 2023-02-15 v2 Artificial Intelligence Machine Learning

Abstract

Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we only modify the special token representations (e.g., [SEP] and [CLS] in BERT) before the self-attention module at each layer in Transformer-based models. PASTA achieves comparable performance to full finetuning in natural language understanding tasks including text classification and NER with up to only 0.029% of total parameters trained. Our work not only provides a simple yet effective way of parameter-efficient tuning, which has a wide range of practical applications when deploying finetuned models for multiple tasks, but also demonstrates the pivotal role of special tokens in pretrained language models

Keywords

Cite

@article{arxiv.2210.04382,
  title  = {Parameter-Efficient Tuning with Special Token Adaptation},
  author = {Xiaocong Yang and James Y. Huang and Wenxuan Zhou and Muhao Chen},
  journal= {arXiv preprint arXiv:2210.04382},
  year   = {2023}
}

Comments

EACL 2023

R2 v1 2026-06-28T03:06:45.979Z