Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

by Jason Wei et al.

Early research on using worked reasoning examples to improve performance on reasoning tasks.

The paper studies how worked reasoning examples affect language-model performance on reasoning tasks. It offers historical context for later approaches without guaranteeing reliable reasoning in every model.

Level: Advanced
Models: any
Category: Prompting
Tags: reasoning, research
Source date: 2022-01-28
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok

Summary in our own words. All rights with the original creator. Correction or removal: DM on X.