Who introduced chain-of-thought prompting?

It was introduced in the 2022 paper 'Chain-of-Thought Prompting Elicits Reasoning in Large Language Models' by Jason Wei and colleagues at Google Research, which showed few-shot worked examples with step-by-step reasoning significantly improved model accuracy on reasoning tasks.

What is zero-shot chain-of-thought?

It's a simplified variant, introduced by Takeshi Kojima and colleagues, showing that appending a simple instruction like 'Let's think step by step' — without any worked examples — can trigger much of the same reasoning benefit as full few-shot chain-of-thought prompting.

Does chain-of-thought prompting work on all models?

Research has found the benefit tends to emerge more strongly in sufficiently large, capable models; smaller models sometimes show little benefit or can even perform worse with chain-of-thought prompting compared to direct answering.

How is chain-of-thought different from a dedicated reasoning model?

Chain-of-thought prompting is a prompting technique applied to a general-purpose model at inference time. Dedicated reasoning models like o1/o3 or DeepSeek-R1 are specifically trained, often via reinforcement learning, to generate effective long reasoning traces as an intrinsic capability, generally outperforming prompted CoT on hard reasoning tasks.

What is self-consistency in relation to chain-of-thought?

Self-consistency is a technique that samples multiple independent chain-of-thought reasoning paths for the same problem and takes the majority-vote final answer across them, which tends to improve accuracy over relying on a single reasoning path.

Does chain-of-thought reasoning always reflect the model's true internal computation?

Not necessarily — research has shown that a model's stated chain-of-thought reasoning can sometimes be an unfaithful post-hoc rationalization rather than a fully accurate description of the computation that actually produced its answer.

AI Fundamentals

Chain-of-Thought Prompting

IntermediateTechnique9K learners

#ChainOfThoughtPrompting #AIFundamentals#Technique#Intermediate#TreeOfThoughts #ReActPrompting #TestTimeCompute #PromptEngineering #ArtificialIntelligence#Glossary#SkillVeris

Definition

Chain-of-thought prompting is a technique that elicits step-by-step intermediate reasoning from a language model — either by instructing it to 'think step by step' or by providing worked examples that reason before answering — which has been shown to substantially improve performance on tasks requiring arithmetic, logic, or multi-step reasoning.

Overview

When a language model is asked to jump directly to a final answer for a complex problem, it effectively must produce the correct answer in a single, unbroken burst of computation constrained by its fixed per-token processing, which is especially error-prone for multi-step arithmetic, logical deduction, or planning problems. Chain-of-thought (CoT) prompting, introduced in a widely cited 2022 Google Research paper by Jason Wei and colleagues, showed that prompting a sufficiently large language model to generate intermediate reasoning steps before its final answer — either via explicit instruction or by including a few worked examples in the prompt that demonstrate step-by-step reasoning — significantly improves accuracy on tasks like grade-school math word problems, commonsense reasoning, and symbolic manipulation, compared to prompting for a direct answer. A simplified and highly influential variant, 'zero-shot chain-of-thought,' introduced shortly after by Takeshi Kojima and colleagues, showed that simply appending a phrase like 'Let's think step by step' to a prompt — with no worked examples at all — was often sufficient to trigger substantial reasoning improvements, making the technique trivially easy to apply. The mechanism is generally understood as giving the model more intermediate computation and 'working memory' in the form of generated tokens: because each generated token can attend to all previous tokens, writing out intermediate steps effectively lets the model use additional forward passes to build toward an answer, rather than compressing an entire multi-step derivation into the computation of a single token. Chain-of-thought prompting was an important precursor to today's dedicated 'reasoning models' (such as OpenAI's o1/o3 series and DeepSeek-R1), which extend the same core idea — reasoning before answering — by training the model via reinforcement learning specifically to produce long, effective internal reasoning traces, rather than relying purely on prompting a general-purpose model. CoT prompting is also foundational to related techniques like self-consistency (sampling multiple chain-of-thought reasoning paths and taking a majority vote on the final answer) and Tree of Thoughts (exploring and backtracking across multiple reasoning branches rather than following a single linear chain).

Key Concepts

Elicits explicit step-by-step intermediate reasoning before a final answer
Introduced in a 2022 Google Research paper by Jason Wei et al.
Zero-shot variant works via a simple instruction like 'Let's think step by step'
Substantially improves accuracy on arithmetic, logic, and multi-step reasoning tasks
Benefit generally scales with model size — smaller models show less improvement from CoT
Provides the model more effective 'working memory' via generated intermediate tokens
Precursor to dedicated reasoning models like OpenAI o1/o3 and DeepSeek-R1
Foundation for related techniques like self-consistency and Tree of Thoughts

Use Cases

Solving multi-step math word problems more accurately

Improving performance on logical and commonsense reasoning benchmarks

Debugging or explaining a model's reasoning process for transparency

Structuring prompts for tasks requiring multi-step planning or decomposition

Serving as the base technique underlying self-consistency and Tree of Thoughts methods

Improving reliability of LLM outputs in agentic and tool-use reasoning loops

Frequently Asked Questions

From the Blog

AI & Technology

Prompt Engineering: Get Better Results from Any LLM

The difference between a mediocre AI output and an excellent one is usually the prompt. This guide covers the techniques that consistently produce better results: clarity, context, examples, chain-of-thought, system prompts, and output formatting — with real before/after examples.