I · ReasoningMature★★

Zero-Shot Chain-of-Thought

also known as Let's Think Step by Step, Trigger-Phrase CoT

Elicit step-by-step reasoning with a single trigger phrase rather than few-shot exemplars.

This pattern helps complete certain larger patterns —

  • specialisesChain of Thought★★— Elicit multi-step reasoning by prompting the model to produce intermediate steps before its final answer.

Context

A team is building prompts for many different reasoning tasks — dozens or hundreds — where writing carefully crafted few-shot examples with full chain-of-thought traces would be expensive in effort and would have to be redone each time the task changes. They want something close to chain-of-thought quality but without paying the per-task curation cost for every new task type.

Problem

Few-shot chain-of-thought needs a small set of worked examples for every distinct task; the work of writing and maintaining those examples does not scale across a large portfolio of tasks or a fast-changing product. Without exemplars, however, plain prompting collapses the reasoning into a single output token and quality drops sharply. The team needs a way to trigger step-by-step reasoning that does not depend on supplying task-specific worked solutions in the prompt.

Forces

  • Trigger phrases are model- and language-specific.
  • Quality lift is smaller than well-curated few-shot CoT.
  • Trigger-phrase reasoning can drift on complex tasks.

Example

A team is building agent prompts for fifty different tasks and writing few-shot CoT exemplars per task is unaffordable. They append a single trigger phrase ('Let's think step by step') to each prompt; the model produces reasoning before its answer with no exemplars required. Quality on multi-step tasks climbs immediately; for the few tasks where zero-shot CoT is not enough, they reach for few-shot or self-consistency on top.

Diagram

Solution

Therefore:

Append a trigger phrase ('Let's think step by step', 'Let's work through this carefully') to the prompt. The model produces reasoning before its answer with no exemplar required. Optionally extract the final answer with a follow-up prompt.

What this pattern forbids. The model is required to reason before answering; one-shot answer-only generation is not the target.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

References

Provenance