Data annotation is the work of turning raw material into training material with answers attached: a review gets tagged positive or negative, the cars ...
A benchmark is a standardised exam for AI models: the questions are fixed, the scoring rules are fixed, and different models answer the same paper so ...
Speculative decoding is a way to make a large language model generate text faster: a much smaller draft model first guesses the next few tokens, and t...
Positional encoding is an extra ordering signal attached to every word in a sentence, so the model knows which token comes first and which follows. Se...
Few-shot learning is a way of using a large model in which you show it only a handful of examples and it completes a new task following their format a...
Prompt injection is a type of attack that hides instructions inside external content a model will read, tricking the model into mistaking data for com...
Pre-training is the first stage of training a large language model: before it learns to chat or write code, the model does one thing over massive amou...
Autoregression is the basic method a large model uses to generate text: it predicts the most likely next token from the tokens that have already appea...
