Exhibit 6.7
7Use
When you type a prompt, a basic language model does not retrieve a ready-made answer from a database. It generates a response token by token, although some modern systems can also call search engines, tools or external knowledge sources.
Why it is in the museum
A modern language model does not appear fully formed. It passes through data collection, training, adaptation, evaluation and, finally, answer generation.
What supports this exhibit
Technical operating principle
That generation proceeds token by token unless the surrounding system also uses external tools or retrieval.
Main source: Autoregressive decoding in the language-model literature.
The source is listed here, but no direct link is currently available in the register.
What to keep in mind: General principle with an important qualification for tool-using and RAG systems.
Ask the exhibit
This small guide uses only the information documented on this exhibit page. If your question goes beyond that evidence, it will say so instead of inventing an answer.
Start with one of the suggested questions above, or type your own.