Crafting a Clear Classification Prompt
A developer is prompting a language model to categorize news headlines. They want the model to respond with only one of three words: 'Politics', 'Sports', or 'Technology'. To prevent the model from giving conversational or varied answers (e.g., 'This headline is about sports'), what specific instruction could be added to the prompt to define the meaning of each possible answer and constrain the output? Provide the exact text of the instruction you would add.
0
1
Tags
Ch.2 Generative Models - Foundations of Large Language Models
Foundations of Large Language Models
Computing Sciences
Foundations of Large Language Models Course
Application in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A researcher is designing an instruction for a language model to determine if a sentence is grammatically sound. The initial instruction is: "Is the following sentence grammatically correct?"
When tested, the model's responses are inconsistent. It sometimes answers "Yes, it is correct," other times "No, that sentence has an error," and occasionally it just provides a corrected version of the sentence.
Which of the following revised instructions would be most effective at solving this problem by clarifying the expected output?
Improving Prompt Reliability for Sentiment Analysis
Crafting a Clear Classification Prompt