Demonstration
Last updated
Last updated
LLMs have the ability to follow demonstrations by example that we have provided, without any explicit instructions or conditions. It's like providing X as input and Y as output.
If we have enough pairs to demonstrate, the LLM will learn and try to predict Y for incoming X.
LLMs have an ability called "in-context learning."
In-context learning comes along with LLMs by providing examples called few-shot or many-shot examples in the prompt.
If you have some experience with training machine learning models, you will notice this concept is similar to preparing a dataset for supervised learning by providing x_train and y_train.