Researchers have developed a new method called SetFit for efficient few-shot learning without the need for explicit prompts. The approach uses a combination of set-based and instance-based methods to learn from small datasets. This allows models to adapt quickly to new tasks with minimal training data. According to the developers, SetFit outperforms other few-shot learning methods in several benchmarks, including those on image classification and natural language processing tasks. --- Why it matters: This matters because it enables AI models to learn from smaller datasets, which is crucial for real-world applications where large amounts of labeled data may not be available. This can speed up the development process and reduce costs associated with training and deploying AI systems. Source: https://huggingface.co/blog/setfit