Learn Before
Concept

Prediction Challenge in Span Masking

A key challenge introduced by span masking is that the model must learn to predict the number of tokens that were originally part of a masked span. This is necessary because spans of varying lengths are all replaced by a single [MASK] token, so the model needs to determine the correct length of the text to generate.

0

1

Updated 2026-04-17

Contributors are:

Who are from:

Tags

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

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences