Learn Before
Short Answer

Modifying a Prompt for Step-by-Step Reasoning

A user wants a language model to solve the following logic puzzle but finds it often gives an incorrect final answer without any justification. Modify the user's prompt to encourage the model to break down its reasoning process before providing the solution.

Original Prompt: 'There are three boxes labeled 'Apples', 'Oranges', and 'Apples and Oranges'. You know that every label is incorrect. You are allowed to pick one fruit from one box to determine the correct labels for all three boxes. Which box should you pick from?'

0

1

Updated 2025-10-02

Contributors are:

Who are from:

Tags

Ch.3 Prompting - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

Application in Bloom's Taxonomy

Cognitive Psychology

Psychology

Social Science

Empirical Science

Science