Large Language Model (LLM)
In one sentence
AI models trained on massive volumes of text that can understand and generate text. Doubao, DeepSeek, ChatGPT, and Claude are all powered by large language models.
Essentially, what an LLM does is predict the most likely next words based on preceding text. The more text used in training and the larger the model, the more complex the tasks it can handle—writing articles, summarizing, translating, writing code, and answering questions.
An LLM does not automatically know internal company data, nor does it know what happened after its training cutoff date. To get answers based on company facts, you need to pair it with a knowledge base, web search, or include the reference materials directly in the prompt.
Example
An employee provides a 30-page product manual to an LLM and asks it to compile 10 frequently asked customer questions and answers.
Related terms
- Generative AI (AIGC)
- AI capable of generating new content such as text, images, audio, and video, as well as the content produced by such AI.
- Prompt
- The instructions and reference materials provided to an AI, specifying what it should do, what information to use, and what format to follow.
- Context window
- The maximum total amount of text an LLM can process at once, including prompts, reference materials, chat history, and its own generated responses.
- Hallucination
- When an AI presents non-existent or incorrect information with full confidence, such as fabricating data, sources, legal clauses, or product features.
