ManySpace
Türkçe Sign in Sign up

AI & MLRecommendedAIML-LM-022

Prompting and In-Context Learning

Steering a pretrained model with instructions and examples in the context window, without weight updates.

Difficulty
3 / 5
Importance
4 / 5
Study time
1–2 h
Kind of work
Mixed

Why it matters

The learner can vary the number and order of in-context examples and predict their effect on a model's answer.

The route to this topic

Route AIML-LM-022
What Is a Model? Tasks: Regression, Classification, and Beyond Features and Targets Classification Framing Linear Regression I: Prediction and Residuals Embeddings Tokens and Tokenization Scores and Logits Loss and Fitting: Squared Error Similarity in Vector Space Multiclass Scores and Softmax Autoregression Query, Key, Value Similarity Scores Next-Token Prediction Weighted Aggregation Self-Attention Context and Conditioning Prompting and In-Context Learning