Short Answer

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

Updated 2025-10-10

Contributors are:

Who are from:

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