Example

Example of Token Reordering in Denoising Autoencoding

In denoising autoencoding, token reordering trains an encoder-decoder model to reconstruct a coherent sequence from an input where the words have been shuffled. For example, if a model is presented with the corrupted sequence [C] . kitten the chasing The is ball, it must learn to generate the original text in its correct order: The kitten is chasing the ball ., typically predicting each token autoregressively.

0

1

Updated 2026-04-17

Contributors are:

Who are from:

Tags

Foundations of Large Language Models

Ch.1 Pre-training - Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences