← Dictionary / Large Language Model (LLM)

Large Language Model (LLM)

Appears in 1 paper

A neural network trained to predict the next token in a sequence, using next-token prediction as the training objective.

As used in Paper 14 — Chain-of-Thought Prompting Elicits Reasoning in Large Language Models →

A neural network trained to predict the next token in a sequence, using next-token prediction as the training objective. CoT demonstrates that LLMs, despite their simple training objective, can learn to reason when shown appropriate examples. Modern LLMs (GPT-3, PaLM, Claude, etc.) all use CoT variants in production.

Appears in papers

Paper 14 — Chain-of-Thought Prompting Elicits Reasoning in Large Language Models →