What is LLM (Large Language Model)? A large language model (LLM) is a neural network trained on very large amounts of text to predict the next token, which lets it write, summarise, translate, answer questions and write code. LLM (Large Language Model) explained An LLM learns patterns in language by reading huge amounts of text and predicting what comes next. That single skill, at scale, lets one model draft emails, summarise documents, translate, answer questions and write code.Most modern LLMs use the Transformer architecture, introduced in 2017 as a design based solely on attention mechanisms (Vaswani et al., 2017). Scale mattered: GPT-3, an autoregressive model with 175 billion parameters, performed many tasks from a few examples in the prompt, without any gradient updates or fine-tuning (Brown et al., 2020). Well-known model families today include GPT, Claude and Gemini, alongside open-weight models.LLMs have limits. They can state wrong facts with confidence, they cannot see data they were not given, and they have a finite context window. Teams reduce these risks with retrieval-augmented generation (RAG), clear prompts, tool use and evaluation.To choose an LLM for a business task, compare accuracy on your own examples, cost per token, speed, data-privacy terms and how reliably it follows instructions, rather than relying on a public leaderboard alone. How Groovy Web uses LLM (Large Language Model) We choose and route between LLMs per task, measure each on real examples, and add retrieval and guardrails so answers are grounded in your data. Explore our Generative AI Development service → LLM (Large Language Model): common questions What is LLM (Large Language Model)? A large language model (LLM) is a neural network trained on very large amounts of text to predict the next token, which lets it write, summarise, translate, answer questions and write code. What should I know about LLM (Large Language Model)? An LLM learns patterns in language by reading huge amounts of text and predicting what comes next. That single skill, at scale, lets one model draft emails, summarise documents, translate, answer questions and write code.Most modern LLMs use the Transformer architecture, introduced in 2017 as a design based solely on attention mechanisms (Vaswani et al., 2017). How does Groovy Web use LLM (Large Language Model)? We choose and route between LLMs per task, measure each on real examples, and add retrieval and guardrails so answers are grounded in your data. Which terms are related to LLM (Large Language Model)? LLM (Large Language Model) is closely related to Transformer Architecture, Token (AI/LLM), Context Window and Prompt Engineering. Related terms Transformer Architecture The Transformer is the neural network architecture behind all modern LLMs, using self-attention mechanisms to process and generate sequences of data. Token (AI/LLM) A token is the basic unit of text that AI language models process, roughly three quarters of an English word, and the basis for LLM pricing and context limits. Context Window The maximum amount of text that a language model can consider when processing input, including both the user's prompt and the model's previous responses in a conversation. Prompt Engineering Prompt engineering is the practice of designing and testing the instructions, examples and context given to a language model so it produces accurate, consistent and useful output. Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) is an AI architecture that combines a language model with a search system to answer questions using your own data. Fine-Tuning (AI) Fine-tuning is the process of further training a pre-trained AI model on your specific data to improve its performance for your particular use case. ← More in Models & Architecture · All 107 glossary terms
