Выборка Top K

AbstractThis work studies the widely adopted ancestral sampling algorithms for auto-regressive language models. We use the quality-diversity (Q-D) trade-off to investigate three popular sampling methods (top-k, nucleus and tempered sampling). …...

AbstractToday’s probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics (e.g., perplexity). This …...