Zero-shot prompting is a fundamental prompt engineering technique where a large language model (LLM) is asked to perform a task using only a natural-language instruction, without any task-specific examples provided in the prompt. The model relies entirely on knowledge acquired during pretraining to understand and execute the task.¹⁾

In standard zero-shot prompting, the user provides a task description and input directly to the model. The prompt takes the form:

[Task instruction]
[Input]
[Output indicator]

For example, a sentiment classification task might be prompted as:

Classify the following text as positive or negative.
Text: "The movie was absolutely wonderful."
Sentiment:

The model generates its response based solely on patterns learned during pretraining, without any demonstrations of the expected input-output mapping.

A landmark advancement in zero-shot prompting was introduced by Kojima et al. (2022) in their paper “Large Language Models are Zero-Shot Reasoners.”²⁾ The authors discovered that simply appending the phrase “Let's think step by step” to a prompt triggers multi-step reasoning in LLMs without any demonstrations.

This technique, called Zero-Shot Chain-of-Thought (Zero-Shot-CoT), operates in two stages:

1. Reasoning extraction: The prompt includes the trigger phrase, causing the model to generate intermediate reasoning steps.
2. Answer extraction: A follow-up prompt extracts the final answer from the generated reasoning.

Zero-Shot-CoT produced dramatic improvements over standard zero-shot prompting on reasoning benchmarks:³⁾

The approach also outperformed standard few-shot prompting (without CoT) on GSM8K, improving from 17.9% to 58.1%.

Zero-shot prompting is most appropriate when:

• No examples are available or curating them is costly.
• Quick evaluation of model capabilities on a new task is needed.
• Task-agnostic deployment is desired, as a single prompt template works across domains.
• Simple, well-defined tasks such as classification, translation, or summarization are involved.
• Rapid prototyping before investing in few-shot example curation.

• Underperforms few-shot methods: Without demonstrations, the model lacks task-specific guidance, often trailing few-shot or few-shot-CoT approaches on complex tasks.⁴⁾
• Model-scale dependent: Zero-shot reasoning gains are most pronounced in very large models (100B+ parameters) and diminish significantly in smaller models.
• Post-processing required: Zero-Shot-CoT's two-stage process requires additional prompt engineering to extract formatted answers.
• Not universally effective: Fails on tasks requiring specialized domain knowledge or precise formatting not captured during pretraining.
• Sensitivity to phrasing: Small changes in instruction wording can produce significantly different outputs.

• Prompt Engineering
• Few-Shot Prompting
• chain_of_thought_prompting
• Active-Prompt
• Automatic Prompt Engineer (APE)