Also known as: llm Β· LLM (Large Language Model) Β· LLM Β· Large Language Model (LLM) Β· Large Language Models (LLMs) Β· Large Language Models
LLM, or large language model, is a language model with a large number of parameters trained on broad text or multimodal data to understand and generate language. LLMs can perform tasks such as answering questions, summarizing, drafting, coding, translation, and reasoning-like text generation, but their outputs require evaluation and governance.
A language model with a large number of parameters (typically at least a billion) that are adjusted during training. Due to its size, it requires a lot of data and computing capability to train. Large language models are usually based on the transformer architecture.
At a minimum, a language model having a very high number of parameters. More informally, any Transformer-based language model, such as Gemini or GPT. See Large language models (LLMs) in Machine Learning Crash Course for more information.
A text-driven foundational model that's trained on a vast amount of data. LLMs are used to perform natural language processing (NLP) tasks, such as text generation, machine translation, text summarization, and question answering. LLMs are text-based, whereas foundation models can be trained with and receive input from multiple modalities, including text, images, audio, and video.
A side-by-side comparison of Large Language Model and Language Model. Understand why an LLM is a large-scale form of language model with broader task capabilities and governance needs.
A side-by-side comparison of Large Language Model and Foundation Model. Understand why an LLM is language-centered, while a foundation model is a broad pretrained base model that can support many downstream tasks.
A side-by-side comparison of Generative AI and Large Language Model. Understand why generative AI is a broader content-producing category, while an LLM is a language-focused model type often used inside generative AI systems.