What is In-Context Learning?

The input instructions and context provided to a generative model.

Learning or adapting behavior from only a small number of examples.

Methods that allow systems to learn patterns from data and improve over time.

Learning patterns from unlabeled data without explicit target outputs.

A language-agnostic tokenizer that learns subword units directly from raw text without pre-splitting on whitespace.

Predicting the user's purpose from a text query to route it correctly.