Learn Before
Concept

Binary Classification System for Next Sentence Prediction

In the Next Sentence Prediction (NSP) task, the relationship between two sentences is evaluated by classifying each training sample into a binary label set, consisting of IsNext\mathrm{IsNext} and NotNext\mathrm{NotNext}. The model processes the input sequence and utilizes the encoder's output vector for the initial [CLS] token. This vector, denoted as hcls\mathbf{h}_{\mathrm{cls}} (or h0\mathbf{h}_0), serves as the sequence representation. A classifier is then constructed on top of hcls\mathbf{h}_{\mathrm{cls}} to predict the correct sequence label.

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

Related