Large language model

A large language model, or LLM, is a neural text model trained on large corpora to predict, generate, transform, and reason over language and code.

Large language models use transformer-style architectures and large-scale pretraining to learn statistical patterns in text, code, and sometimes multimodal data. In products, they are used for chat, summarization, coding, retrieval-augmented generation, classification, extraction, and agent workflows. Quality depends on training data, post-training, context handling, tool use, evaluation, and dep...