# Large 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.

- Identifier: PTL-0102
- Category: Foundations
- Canonical URL: https://protologue.com/t/large-language-model/
- Also known as: LLM, language model

## 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.

## Broader terms

- [Foundation Model](https://protologue.com/t/foundation-model/)

## Narrower terms

- [Base Model](https://protologue.com/t/base-model/)

## Related terms

- [Token](https://protologue.com/t/token/)
- [Prompt](https://protologue.com/t/prompt/)
- [In-Context Learning](https://protologue.com/t/in-context-learning/)

## Sources

- Zhao et al. (2023). A Survey of Large Language Models. https://arxiv.org/abs/2303.18223
- Brown et al. (2020). Language Models are Few-Shot Learners. https://arxiv.org/abs/2005.14165

## 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/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)