Self-consistency

As explained in The Art of AI Product Development

Self-consistency is a prompting technique that samples multiple reasoning or response paths and selects or synthesizes the answer supported by the most consistent results.

Self-consistency turns language-model randomness into a selection process: generate several reasoning or response paths, then retain the result best supported by agreement or evaluation. It helps extend prompting beyond simple tasks toward complex, creative, or multistep outputs. section 6.3 section 6.3.2

Choose the selection method according to the output:

• Use majority voting for categorical answers with a definite ground truth, such as sentiment analysis. section 6.3.2
• Ask the model to score open-ended outputs, or apply a stronger external check when one exists. section 6.3.2
• Budget time and resources for repeated calls, and monitor prompts continuously against real-world interactions. section 6.3.2 section 6.5

Content-generation experiment

Generate three LinkedIn posts announcing a May 25, 2025, webinar about complying with the EU AI Act. Ask the model to critically score each post from 1 to 10 and return the results as a JSON array. section 6.3.2

Figure 6.6 Schema of self-consistency prompting

Use the schema to visualize repeated generation followed by output selection. section 6.3.2

Figure 6.7 Double diamond model of a creative process

Use the double diamond to frame broad creative exploration followed by convergence on a preferred solution. section 6.3.2

How The Art of AI Product Development covers it

How deep it goes

Explains repeated sampling, voting, self-scoring, and testing, but stops short of implementation detail beyond temperature settings.

Examples

Demonstrates sentiment-analysis voting, unit-test validation, and scored LinkedIn-post variants for an EU AI Act webinar.

What it assumes

Assumes familiarity with basic prompting and introduces repeated model calls as a response to few-shot prompting limits.

What you can do after

Apply it by generating multiple prompt outputs and choosing through voting, scoring, or a confidence-building external check.

How it connects

Connects self-consistency with few-shot prompting, chain-of-thought prompting, reflection prompts, majority voting, and the double diamond model.

liveBookmanning.com

Read The Art of AI Product Development on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionSelf-consistency is an evaluation technique that compares multiple independently generated answers to the same input to estimate answer reliability.
• 

  liveBookmanning.com
  Build a Reasoning Model (From Scratch)An inference technique that generates multiple candidate responses and selects or combines them to improve answer quality.
• 

  liveBookmanning.com
  Generative AI in ActionA self-consistency check compares multiple generated results or reasoning paths to identify inconsistent or unreliable outputs.
• 

  liveBookmanning.com
  AI Agents in ActionSelf-consistency is a reasoning technique that samples multiple candidate reasoning paths and selects an answer supported by their agreement.
• 

  liveBookmanning.com
  Prompt Engineering in PracticeSelf-consistency is a sampling technique that generates multiple reasoning paths and selects or aggregates the conclusion that is most consistent across them.

Compare how 6 books explain self-consistency →

Related concepts

• chain-of-thought promptinguses · Chain-of-thought prompting is a technique that elicits or guides a model to produce or follow intermediate reasoning steps before a final answer.
• hallucinationaddresses · A hallucination is model-generated content that is false, fabricated, or unsupported by relevant evidence but presented as plausible or factual.
• modeuses · The statistical mode is the value or category occurring most frequently in a set of observations or outcomes.
• best-of-Nalternative to · Best-of-N is a technique that generates or evaluates multiple candidates and selects one according to a scoring or quality criterion.
• samplingused by · Sampling is a procedure for selecting or generating observations, values, or outcomes from a larger population, signal, or probability distribution according to a specified method.
• language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.

This explainer was generated by Manning's knowledge graph from the text of The Art of AI Product Development. The section links point to the parts of the book it draws on.