Primer
  • Factored Cognition Primer
  • Intro
    • Factored Cognition
    • Before We Start
  • Chapters
    • Hello World
    • Question Answering
      • Q&A without context
      • Q&A about short texts
    • Debate
      • Representing debates
      • From debates to prompts
      • The debate recipe
    • Long Texts
      • Loading paper text
      • Finding relevant paragraphs
      • Answering given paragraphs
    • Amplification
      • Asking subquestions
      • Answering subquestions
      • One-step amplification
      • Recursive amplification
    • Verifiers
      • Checking answers
      • Checking reasoning steps
    • Tool Use
      • Web search
      • Interpreters
    • Deduction
      • Chain of Thought
    • Action Selection
      • One-shot action selection
      • Iterative action selection
    • Amplification Revisited
  • Appendix
    • What’s next?
  • Links
    • We’re Hiring
    • Our Slack Community
    • ICE on Github
Powered by GitBook
On this page
  • What is factored cognition?
  • Why factored cognition?
Edit on GitHub
  1. Intro

Factored Cognition

Decomposition of reasoning tasks

PreviousFactored Cognition PrimerNextBefore We Start

Last updated 2 years ago

What is factored cognition?

refers to the idea of breaking down (or factoring) sophisticated learning and reasoning tasks into many small and mostly independent tasks.

We’ll call programs that describe how to break down a task recipes.

Why factored cognition?

We can think about machine learning systems on :

  • Process-based systems are built on human-understandable task decompositions, with direct supervision of reasoning steps.

  • Outcome-based systems are built on end-to-end optimization, with supervision of final results.

Factored cognition is a prerequisite for making the reasoning processes of large language models explicit so that they can be supervised more easily.

Factored cognition
a spectrum from process-based to outcome-based