Short Answer

Emergence of Factual Knowledge from Self-Supervision

A large language model is trained on a massive dataset of internet text with the sole objective of predicting a randomly masked word in a sentence. Explain how this simple task enables the model to learn factual information, such as 'The capital of France is Paris,' even though this fact is never explicitly labeled as 'fact' in the training data.

0

1

Updated 2025-10-07

Contributors are:

Who are from:

Tags

Ch.2 Generative Models - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

Analysis in Bloom's Taxonomy

Cognitive Psychology

Psychology

Social Science

Empirical Science

Science