SetFit: Efficient Few-Shot Learning Without Prompts

This post introduces SetFit, a new parameter-efficient fine-tuning method for few-shot learning. SetFit utilizes a Siamese network architecture and contrastive learning to train models on small labeled datasets, achieving high accuracy without prompts. It involves a two-stage training process: first, training a Siamese network on unlabeled data to generate synthetic labels, and second, fine-tuning a classification model on these synthetic labels. The post provides benchmarks demonstrating SetFit's competitive performance against other few-shot learning methods.