Re:Inductive or Deductive? Rethinking the Fundamental Reason...
by HarHarVeryFunny on Tuesday September 03, 2024 @02:28PM
(#41437665)
LLMs are statistical next-word predictors, wrapped in a stochastic next-word generator.
The next-word predictions output by the model itself are based on the patterns and statistics of the training set. The next word that is actually generated is typically a random selection per a top-k or top-p sampling scheme.
The next-word predictions output by the model itself are based on the patterns and statistics of the training set. The next word that is actually generated is typically a random selection per a top-k or top-p sampling scheme.