BERT vs GPT Pre-training

Easy

llms Google OpenAI Meta

Multiple Choice

BERT is pre-trained with masked language modeling (bidirectional); GPT is pre-trained with causal language modeling (left-to-right) BERT generates text; GPT classifies text BERT uses reinforcement learning; GPT uses supervised learning BERT processes tokens in parallel; GPT processes tokens sequentially during training

Correct!

Incorrect — try again next time!

Upgrade to Pro to unlock solutions and explanations