Skip to content
Vinony
English
EnglishBahasa IndonesiaDeutschEspañolFrançaisItalianoNederlandsPolskiPortuguêsSvenskaTiếng ViệtTürkçeРусскийالعربيةفارسیहिन्दीไทย한국어中文日本語
large language model

File:The_number_of_publications_about_Large_Language_Models_by_year.png · Wikimedia Commons · See Wikimedia Commons

EntityQ115305900· pop 66· linked from 1,009 articles

large language model

Sign in to save

Also known as LLM, LLMs, large language models, word soup machine, word soup model, word salad machine, word salad model

language model built with very large amounts of texts

AI overview

A large language model is a computer system trained on vast amounts of text data to understand and generate human language. It matters because it can perform a wide range of language tasks—like answering questions, writing, and translation—which makes it useful for many practical applications.

AI-generated from the Wikipedia summary — may contain errors.

Research

21,809 papers

via PubMed

Described at

youtube.com →

Link to a page describing this subject · not written by Vinony

Wikidata facts

Subclass of
language model
Has use
computer security
Show 10 more facts
Stack Exchange tag
softwarerecs.stackexchange.com/tags/llm
Commons category
Large language models
facet of
Artificial intelligence
short name
LLM
uses
transformer
on focus list of Wikimedia project
WikiProject Artificial Intelligence
topic's main category
Category:Large language models
described at URL
www.youtube.com/watch?v=WqYBx2gB6vA
opposite of
small language model
has list
list of large language models
Sources (3)

via Wikidata · CC0

~40 min read

Encyclopedic overview

A large language model (LLM) is a neural network trained on a vast amount of text for natural language processing tasks, especially language generation. LLMs can typically generate, summarize, translate and analyze text in many contexts, and are a foundational technology behind modern chatbots. Biased or inaccurate training data can make an LLM's output less reliable.

As of 2026, the most capable LLMs are based on transformer architectures, which, according to the 2017 paper "Attention Is All You Need", can be more efficient and parallelizable than earlier statistical and recurrent neural network models.

Excerpted from Wikipedia’s “large language model” article, available under the CC BY-SA 4.0 licence.

Gallery (7)

Available in 66 languages

Show 47 more

via Wikidata sitelinks · CC0