ClassroomThe classroom
Back to the lesson libraryMECHANISM · 12 MIN
M26.7 CONNECT THE MECHANISM

Choose how information should reach the model

"Just paste the whole help center in." "No, fine-tune it." "No, keep RAG." Settle the argument with a decision table and some token arithmetic.

LESSON OVERVIEW12 min lesson

Lesson overview

"Just paste the whole help center in." "No, fine-tune it." "No, keep RAG." Settle the argument with a decision table and some token arithmetic.

What you’ll explore

  • Retrieval, long context, fine-tuning, and learned model memory solve different information-access or behavior problems; choose and combine them using freshness, provenance, quality, and cost evidence.
GO TO THE SOURCE

Original explanations, connected to the research.

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., 2020)Lost in the Middle: How Language Models Use Long Contexts (Liu et al., 2023)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.