How deeply does Generative AI in Action cover few-shot chain of thought?

Defines the prompt pattern and shows worked arithmetic, but omits implementation code for the completion API call.

Few-shot chain of thought

Few-shot chain of thought is a prompting technique that provides a small number of examples containing reasoning chains before asking the model to solve a new instance.

Few-shot chain of thought (CoT) prompts a language model with a small set of examples that include high-quality reasoning chains, then asks it to solve a new instance. The examples demonstrate both the task format and a step-by-step solution pattern. section 6.4.5

Use the technique to:

Improve accuracy and reliability on tasks such as question answering, translation, and code generation. section 6.4.5
Distinguish example-driven few-shot CoT from zero-shot CoT, which adds an instruction such as “Take a step-by-step approach.” section 6.4.5

Arithmetic prompt pattern

Provide worked examples such as calculating computers installed over several days or golf balls remaining after losses, then pose a similar question and request the final answer.

How Generative AI in Action covers it

liveBook manning.com

Read Generative AI in Action on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Prompt Engineering in PracticeA prompting technique that provides worked examples demonstrating intermediate reasoning steps.

Compare how 2 books explain few-shot chain of thought →

Related concepts

chain-of-thought promptingkind of · Chain-of-thought prompting is a technique that elicits or guides a model to produce or follow intermediate reasoning steps before a final answer.
demonstrationuses · A demonstration is an example pairing an input, request, or prompt with a corresponding output, answer, or label to illustrate a task or expected behavior.
few-shot learninguses · Few-shot learning is the adaptation or performance of a model on a task using only a small number of task-specific examples.

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