BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models

We show that with small-to-medium training data, fine-tuning only the bias terms (or a subset of the bias terms) of pre-trained BERT models is competitive with (and sometimes better than) fine-tuning the entire model. For larger data, bias-only fine-tuning is competitive with other sparse fine-tuning methods. Besides their practical utility, these findings are relevant for the question of understanding the commonly-used process of finetuning: they support the hypothesis that finetuning is mainly about exposing knowledge induced by language-modeling training, rather than learning new task-specific linguistic knowledge.