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
Edit on GitHub
  1. Chapters

Long Texts

Answering questions about research papers

PreviousThe debate recipeNextLoading paper text

Last updated 2 years ago

Ultimately we’d like for language models to help us make sense of more information than we can read and understand ourselves. As a small step in that direction, let’s make a recipe that answers questions about research papers.

To do so, we’ll:

In this tutorial, we’ll take a simple approach to step 2: We’ll classify for each paragraph whether it answers the question or not. We then take the paragraphs with the highest probability of answering the question and ask a model to answer the question given those paragraphs, reusing .

Parse and load papers
Find the relevant parts of papers
Answer given those relevant parts
the question-answering recipe