Concept
Zero-shot
Zero-shot means asking a model to perform a task it was never explicitly trained or fine-tuned to do, giving it only a natural-language description of what you want and no worked examples. Contrast this with the standard supervised setup, where you would collect labeled data…
The rest of “Zero-shot” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→