Zero-Shot Learning
The capability of a machine learning model to correctly perform a complex task without ever being explicitly trained on labeled examples of that task.
Think of It Like This
Like a chef who has never seen or cooked a specific exotic dish before, but perfectly creates it just by reading a quick description.
This emergent phenomenon is heavily associated with massive LLMs. Because the model has read trillions of tokens during pre-training, it can generalize its deep understanding of language to completely novel domains. It allows users to prompt a model to translate a rare language or summarize code without providing any fine-tuning data.