---
id: "wang-self-consistency"
title: "Self-Consistency Improves Chain of Thought Reasoning in Language Models"
creator: "Xuezhi Wang et al."
creator_url: "https://arxiv.org/abs/2203.11171"
url: "https://arxiv.org/abs/2203.11171"
level: "advanced"
level_max: null
category: "prompting"
subcategory: "reasoning-and-structured-output"
region: "West"
license: "open"
license_scope: "linked-resource"
models: ["any"]
source_date: "2022-03-21"
date_added: "2026-10-18"
---

[Prompting](/prompting/index.md)

# Self-Consistency Improves Chain of Thought Reasoning in Language Models

by [Xuezhi Wang et al.](https://arxiv.org/abs/2203.11171)

[Read the original →](https://arxiv.org/abs/2203.11171)

Sample several reasoning paths and take the majority answer.

This research explores choosing an answer by comparing multiple generated reasoning attempts. It highlights a quality-versus-computation trade-off that should be evaluated on the intended task.

Level: [Advanced](/levels/index.md#advanced)
Models: any
Category: [Prompting](/prompting/index.md)
Tags: [reasoning](/tags/reasoning/index.md), [research](/tags/research/index.md)
Source date: 2022-03-21
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok
Prerequisites: Requires implementation experience or critical reading of technical methods and system trade-offs.
Subcategory: [reasoning and structured output](/prompting/reasoning-and-structured-output/index.md)
Region: West
Original language: en
Access: free
Resource reuse: open: Source states by/4.0. Applies to the linked resource, not every referenced model or dataset. [Facet definitions](/about/index.md#facets)

Summary in our own words. Rights remain with the original creator. [Credit and correction policy](/about/index.md#credit-policy).

[Plain-text Markdown copy](/prompting/reasoning-and-structured-output/wang-self-consistency/index.md)