SIGNAL//DESK
AI/MLsrc: curated AI glossary

Zero-shot

Asking an AI to do something new without showing it any practice problems or examples first, relying entirely on what it already knows.

A prompting technique where a model is asked to perform a task based solely on the instruction provided, without including any task-specific input-output pairs in the context window.

Performing a task with no task-specific examples in the prompt, relying solely on the model's pre-trained knowledge (contrast few-shot, which supplies a handful of examples).

evolution

  1. 2009 · history
    Zero-Shot Learning (ZSL) Formalization

    Lampert et al. introduced the concept of learning to recognize object classes not present in the training set by using semantic attribute descriptors.

  2. 2017 · history
    Transformer Architecture

    The 'Attention Is All You Need' paper provided the architectural foundation for models to generalize across tasks without task-specific retraining.

  3. 2020 · history
    GPT-3 Emergence

    OpenAI demonstrated that large language models could perform a wide variety of tasks via zero-shot prompting without any gradient updates.


← all terms