Emergent Analogical Reasoning in Large Language Models

TL;DR

Large language models like GPT-3 can perform analogical reasoning tasks in a zero-shot setting, demonstrating emergent cognitive-like abilities that rival or surpass human performance, especially in pattern induction and problem-solving.

Contribution

This study provides evidence that large language models exhibit emergent analogical reasoning abilities comparable to humans, especially in zero-shot scenarios, marking a significant advance in AI cognition.

Findings

GPT-3 matches or exceeds human performance on analogical tasks

GPT-4 shows even better performance in preliminary tests

Large language models demonstrate emergent reasoning capabilities

Abstract

The recent advent of large language models has reinvigorated debate over whether human cognitive capacities might emerge in such generic models given sufficient training data. Of particular interest is the ability of these models to reason about novel problems zero-shot, without any direct training. In human cognition, this capacity is closely tied to an ability to reason by analogy. Here, we performed a direct comparison between human reasoners and a large language model (the text-davinci-003 variant of GPT-3) on a range of analogical tasks, including a non-visual matrix reasoning task based on the rule structure of Raven's Standard Progressive Matrices. We found that GPT-3 displayed a surprisingly strong capacity for abstract pattern induction, matching or even surpassing human capabilities in most settings; preliminary tests of GPT-4 indicated even better performance. Our results indicate that large language models such as GPT-3 have acquired an emergent ability to find zero-shot solutions to a broad range of analogy problems.