What is Label Smoothing?

Techniques that create modified training examples to improve model generalization.

A parameter-efficient fine-tuning method that adds low-rank adapter matrices.

Human-added labels or metadata used to train or evaluate machine learning models.

A simple reference model used to compare whether more complex approaches actually improve results.

Combining predictions from multiple models to improve robustness or accuracy.

How well a model performs on new, unseen data outside the training set.