protologue

Large Language Model

Also called LLM, language model.

A large language model (LLM) is a neural network, usually a Transformer with billions of parameters, trained on very large text corpora to predict the next token, which lets it generate text and perform many tasks from a prompt.

Description

The defining property is that a single model, without task-specific training, can translate, summarize, answer questions, write code, and follow instructions, with the task specified in the prompt. Most deployed LLMs are base models that have been further instruction-tuned and preference-tuned to behave as assistants. Their capabilities and their failure modes, such as hallucination and prompt sensitivity, both follow from next-token prediction over the prompt.

Sources

  1. Zhao et al. (2023). A Survey of Large Language Models.
  2. Brown et al. (2020). Language Models are Few-Shot Learners.

Cite this entry

Protologue. (2026). Large Language Model. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0102). https://protologue.com/t/large-language-model/

BibTeX
@misc{protologue_large_language_model,
  title = {Large Language Model},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.4.0},
  note = {Entry PTL-0102},
  url = {https://protologue.com/t/large-language-model/}
}

Markdown JSON