A user is prompting a large language model with the following math problem: 'A grocery store has 15 apples. They sell 7 and then receive a new shipment of 20 more. How many apples do they have now?' The model consistently provides an incorrect final answer without showing its work. How should the user modify the prompt to best encourage the model to arrive at the correct solution by breaking down the problem?
0
1
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
Related
Evaluating a Model's Reasoning Strategy
A user is prompting a large language model with the following math problem: 'A grocery store has 15 apples. They sell 7 and then receive a new shipment of 20 more. How many apples do they have now?' The model consistently provides an incorrect final answer without showing its work. How should the user modify the prompt to best encourage the model to arrive at the correct solution by breaking down the problem?
Alternative Phrases for Eliciting Step-by-Step Reasoning
Analyzing the Impact of a Prompting Technique