Large Language Models Quiz 1: 13 July 2025 (May 2025 term)

One at a time (sequentially)

In reverse order

All at once (in parallel)

Only after seeing the full input

Normalize attention scores to a probability distribution

Add non-linearity to the model

To predict the correct class for the loss function

Remove redundant features from the input

GPT uses Masked Language Modeling, BERT uses Causal Language Modeling

GPT uses Causal Language Modeling, BERT uses Masked Language Modeling

Both use Masked Language Modeling

Both use Causal Language Modeling