Constructing a Follow-Up Prompt
A language model was prompted with a question and produced a correct line of reasoning but did not state the final answer, as shown below. Write a single, effective follow-up prompt that incorporates both the original question and the model's reasoning to extract the final answer.
Original Question: "A recipe calls for 2 cups of flour to make 12 cookies. If you want to make 30 cookies, how much flour do you need?"
Model's Reasoning: "First, I need to find out how much flour is needed per cookie. That's 2 cups / 12 cookies = 1/6 cup of flour per cookie. To make 30 cookies, I need to multiply the amount of flour per cookie by the number of cookies I want to make. So, the calculation is (1/6) * 30."
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
Extracting a Final Answer from a Language Model
A language model was prompted with a question. It produced a correct line of reasoning but did not state the final answer, as shown below.
Original Question: "A grocery store has 15 apples. They sell 7 and then buy 12 more. How many apples do they have now?"
Model's Reasoning: "Okay, let's break this down. The store starts with 15 apples. They sell 7, so we subtract 7 from 15, which is 15 - 7 = 8. Then, they buy 12 more, so we add 12 to the current number, which is 8 + 12 = 20."
Which of the following follow-up prompts is best designed to extract the final answer from the model's existing reasoning?
Constructing a Follow-Up Prompt