← Master Index
Vol. 13 Module 13.1 Lecture

Zero Shot

Prompting Techniques

How This Lesson Fits the Module & Volume

Basic prompting established task, context, and format. Zero-shot is the simplest pattern that uses those skills: give the model a clear instruction and ask it to perform the task with no labeled examples in the prompt.

Zero-shot is the baseline for Module 13.1. Later lectures add demonstrations (one-shot, few-shot) and reasoning scaffolds (chain-of-thought). Always measure zero-shot first so you know what the examples are buying.

Learning Objectives

By the end of this lesson, students should be able to:

  • Define zero-shot prompting and contrast it with one-shot and few-shot.
  • Write a zero-shot instruction that includes labels, format, and edge-case rules.
  • Identify tasks where zero-shot is enough versus where examples are needed.
  • Use label lists and output schemas to reduce free-form drift.
  • Explain why model capability and instruction tuning affect zero-shot quality.
  • Design a fair A/B comparison between zero-shot and few-shot on the same task.
Definition

Zero-shot prompting asks a model to perform a task using only natural-language instructions (and optional context), without including any input–output demonstration examples in the prompt.

What “Zero” Means

“Zero” refers to in-prompt demonstrations, not to the model’s pretraining. Modern instruction-tuned models have seen millions of tasks during training; zero-shot prompting activates that prior knowledge with a fresh instruction.

PatternDemonstrations in promptMain lever
Zero-shot0Clear instruction + format
One-shot1Single worked example
Few-shot2+Pattern coverage via examples

A Clean Zero-Shot Classifier

Classify the support ticket into exactly one label: billing | outage | account_access | feature_request | other Rules: - Choose "other" if none fit well. - Reply with the label only (lowercase snake_case). No explanation. Ticket: {{TICKET_TEXT}}

When Zero-Shot Works Well

Good fits

  • Common NLP tasks (summarize, translate, extract).
  • Clear label sets the model already “knows.”
  • Formats the model follows from instructions alone.

Weak fits

  • Idiosyncratic house style or schemas.
  • Subtle decision boundaries between labels.
  • Novel scoring rubrics with private meaning.

Next step

Tighten Zero-Shot Without Examples

Before jumping to demos, squeeze more from zero-shot: enumerate allowed outputs, forbid extras, and define ambiguity policy.

Extract company names from the paragraph. Return a JSON array of strings, sorted alphabetically. If none found, return []. Do not invent companies not present in the text. Paragraph: {{PARAGRAPH}}

Strengths and Tradeoffs

Strengths

  • Shortest prompts; lowest token cost.
  • Fast to prototype and A/B test.
  • No demo curation or leakage risk from examples.

Tradeoffs

  • Weaker on niche formats and edge cases.
  • Label wording can swing accuracy.
  • Harder to convey rare decision rules.
Common Misconception

“Zero-shot means the model never saw this task.” It means you provided no examples in this prompt. Instruction-tuned models often excel at zero-shot precisely because training already covered similar tasks.

Knowledge Check

  1. Short Answer: Define zero-shot prompting. Answer: Performing a task from instructions alone with no in-prompt demonstrations.
  2. True/False: Zero-shot means the model has never been trained on similar tasks. Answer: False.
  3. Multiple Choice: How many demos are in a zero-shot prompt? (a) 0, (b) 1, (c) 3–5. Answer: (a).
  4. Short Answer: Name one way to improve zero-shot without adding examples. Answer: Enumerate labels / fix output format / define ambiguity rules (any).
  5. True/False: You should usually measure zero-shot before adding few-shot demos. Answer: True.
  6. Multiple Choice: Zero-shot is often weakest for: (a) common summarization, (b) idiosyncratic private rubrics, (c) translating English to Spanish. Answer: (b).
  7. Short Answer: What should a classifier prompt request when unsure? Answer: An explicit fallback label such as other / unknown (as defined).
  8. True/False: Asking for “label only” can reduce formatting noise. Answer: True.
  9. Multiple Choice: After weak zero-shot on a custom schema, try next: (a) one/few-shot demos, (b) delete the schema, (c) random temperature 2.0 only. Answer: (a).
  10. Short Answer: Why is zero-shot cheap? Answer: No demonstration tokens; shorter prompts.

Key Takeaways

  • Zero-shot = instructions + context, zero demonstrations.
  • It is the baseline against which one-shot and few-shot gains are measured.
  • Label lists and strict formats often unlock most of the available quality.
  • Next: One Shot.
Trainer’s Guide

Hands-on idea: Run the same 20 tickets with (1) a vague zero-shot prompt and (2) a label-enumerated zero-shot prompt; score accuracy before adding any demos.

Discussion prompt: When is a bad zero-shot result a prompting problem versus a model-capability problem?

Recap: Zero-shot solves tasks from instructions alone and sets the Module 13.1 baseline. Continue with One Shot.