Home
Back to Glossary

LLM

Pages
13
References
6
Related Terms
12

Definition

An LLM is a large language model trained on large text corpora to understand, generate, summarize, and transform natural language.

Background

Transformer-based deep learning, large datasets, and large-scale compute made LLMs a foundation for chat interfaces, code generation, question answering, and text automation.

Position

LLMs sit at the center of RAG, MCP, agents, prompting, fine-tuning, and Knowledge Graph-connected applications.

Distinctions

  • LLMs are a major form of generative AI, but generative AI also includes image, audio, video, and other model types.
  • An LLM is not a knowledge base by itself; retrieval, tools, and memory systems are added when external knowledge is needed.

Primary source-backed reference selected for this concept.

A concept map for LLM.

Page Context

  • AI Coding Practices: Engineering for a Higher Probability of Success
    | Permissions, sandboxing, PRs, rollback, review | 3. Research Background and Current Direction Software engineering agents have moved from single-shot code generation toward re...
    Quote: AI Coding Practices: Engineering for a Higher Probability of Success

    developer-tools

  • AI/LLM/Ontology/Organizational Memory
    1. Executive Summary Rather than being a "knowledgeable entity," modern LLMs are probabilistic pattern generators that learn from large volumes of language, code, images, and be...
    Quote: AI/LLM/Ontology/Organizational Memory

    ai-systems

  • Language Games, Intentionality, and LLMs
    Language Games, Intentionality, and LLMs 1. Executive Summary The philosophical question raised by LLMs is not only whether they possess inner understanding. A more useful quest...
    Quote: Language Games, Intentionality, and LLMs

    philosophy-knowledge

  • LLM Limits and Hallucinations: Factuality, Evaluation, and QA
    LLM Limits and Hallucinations: Factuality, Evaluation, and QA 1. Executive Summary LLMs generate plausible text, but they are not truth checkers. Training optimizes next-token p...
    Quote: LLM Limits and Hallucinations: Factuality, Evaluation, and QA

    ai-systems

  • LLM Principles, Explained: From Tokenization to Context Length
    1. Executive Summary An LLM may look as if it reads text directly, but in practice it receives a sequence of tokens and computes probabilities for the next likely token. It is m...
    Quote: LLM Principles, Explained: From Tokenization to Context Length

    ai-systems

  • How LLM Training, Fine-Tuning, RAG, and Agents Differ
    How LLM Training, Fine-Tuning, RAG, and Agents Differ 1. Executive Summary The most common mistake in LLM discussions is to treat pretraining, fine-tuning, prompting, RAG, tool ...
    Quote: How LLM Training, Fine-Tuning, RAG, and Agents Differ

    ai-systems

Pages