Generalization Glossary

Browse 8 generalization terms defined in plain English, from the cultural dictionary of computing.

8 Generalization Terms

Blanket Statement: A broad claim that applies the same conclusion to many cases without enough nuance, distinction, or evidence. In technical arguments, blanket statements are...
Goal Misgeneralization: A failure mode in which a system generalizes the wrong objective or proxy when placed in new situations, even though it appears to perform well during...
In-Context Learning: A model behavior where examples placed in the prompt shape predictions without updating model weights. It influences how models are trained, evaluated, or...
Out-of-Distribution: Describing inputs or situations that differ meaningfully from the data or conditions a model encountered during training. Out-of-distribution cases are...
Overfitting: When a model learns the training data too well — including its noise and random fluctuations — and fails to generalize to new, unseen data. The model has...
Underfit: To train a model that is too simple or insufficiently learned to capture the underlying pattern in the data.
Zero-Shot: Describing a setting where a model performs a task without being given task-specific examples in the prompt, relying instead on prior training and general...
Zero-Shot Learning: The ability of a model to perform a task it was never explicitly trained on, by leveraging its general knowledge. GPT answering questions about a topic it...