Skip to content
Science, DecodedContext Jamming

Paper Reading Lab

Are Emergent Abilities of Large Language Models a Mirage?

Rylan Schaeffer, Brando Miranda, Sanmi Koyejo · 2023

arXiv preprint; published at NeurIPS 2023Open paper ↗PDF ↗

Why this paper

A model of scientific skepticism. It does not say the earlier observations were fabricated; it shows that a measurement choice can manufacture a dramatic-looking pattern.

Pass 1 of 8

Research question

What is the question?

Where to look: Abstract and Introduction

Your read

Background: Module 8, The Scientific Skeptic’s Toolkit →