Skip to the document
Madhuopen lab
Outcome School · Training and alignment13 min read

by Amit Shekhar · 24 April 2026

LoRA - Low-Rank Adaptation of LLMs

LoRA - Low-Rank Adaptation of Large Language Models.

2,451 words#llm#ai#machine-learning4 recall cards

LoRA - Low-Rank Adaptation of LLMs
Read on Outcome School ↗then come back to lock it in
Before you read, guess

How is the weight update ΔW mathematically defined in LoRA using matrices A and B?

Ten seconds, a guess, then read — a wrong guess still makes the answer stick.

What this article covers

  1. The Big Picture
  2. Why Full Fine-Tuning Is Expensive
  3. The Core Idea Behind LoRA
  4. How LoRA Works Step by Step
  5. A Small Numeric Example
  6. Where LoRA Is Applied in a Transformer
  7. Merging LoRA Back Into the Model
  8. Real-World Use Cases

The article lives on outcomeschool.com. Read it there, then come back: the tutor in the margin has read it and will answer questions, and the questions below check what stayed.

Before you go

In one sentence, what was this chapter about?

From memory, without scrolling up. Writing it is what makes it yours; the grade is only to show you what you had.

How sure?