Consider the following instruction given to a language model: 'I will provide a sentence with a grammatical error, followed by the correction. Your task is to fix the grammar in the new sentence I give you. Example: "She don't like coffee." -> "She doesn't like coffee." Now, correct this sentence: "They is going to the park."' This instruction is a valid example of a prompt that relies solely on a direct command without providing any examples to guide the model.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Computing Sciences
Foundations of Large Language Models Course
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A user wants an AI assistant to fix grammatical errors in a sentence. Which of the following instructions best accomplishes this task by relying solely on a direct command, without showing the AI any examples of corrections?
Crafting a Direct Instruction for Grammar Correction
Consider the following instruction given to a language model: 'I will provide a sentence with a grammatical error, followed by the correction. Your task is to fix the grammar in the new sentence I give you. Example: "She don't like coffee." -> "She doesn't like coffee." Now, correct this sentence: "They is going to the park."' This instruction is a valid example of a prompt that relies solely on a direct command without providing any examples to guide the model.