liveBook · Manning

Large language model

As explained in Rearchitecting LLMs

A large language model is a neural language model trained on extensive text data to understand and generate language.

A large language model (LLM) is trained on extensive text collections spanning languages and subject areas. Some have hundreds of billions of parameters, approaching a trillion, and can write, analyze documents, generate code, and translate. section 1.0

Broad capability can be inefficient for specialized work. For example, extracting metrics from legal documents and writing client reports require different strengths. Detailed prompts can guide behavior, but do not change a model’s underlying expertise. section 1.0 section 1.1.2

A smaller language model can be adapted to specific data, tasks, and deployment constraints by changing its architecture. This differs from retrieval-augmented generation, which supplies external information, and fine-tuning, which further trains a model on task-specific data. These approaches can also complement one another. section 1.0 section 1.1.2

How Rearchitecting LLMs covers it

How deep it goes
Defines training scale and capabilities, then motivates architectural adaptation without detailing transformer internals.
Examples
Uses financial-document extraction and report generation, plus pharmaceutical workloads used only a few times daily.
What you can do after
Evaluate whether a general-purpose model mismatches a task and motivate a smaller specialized alternative.
How it connects
Connects large language models to small language models, prompt engineering, retrieval-augmented generation, and fine-tuning.

Also explained in

Compare how 6 books explain large language model →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Rearchitecting LLMs. The section links point to the parts of the book it draws on.