Constructing a Few-Shot Prompt for Ticket Classification
You are tasked with using a large language model to categorize customer support tickets into one of three categories: 'Technical Issue', 'Billing Inquiry', or 'General Feedback'. To ensure the model performs this task accurately, you need to provide it with examples. Construct a complete prompt that includes at least one example for each category and then asks the model to classify a new, uncategorized ticket: "My internet connection keeps dropping."
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Creation in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
A developer is trying to use a large language model to classify the sentiment of movie reviews. They provide the model with the following text, but the model consistently produces unreliable classifications for the final review.
Prompt Text:
Classify the sentiment of the following movie reviews as 'Positive' or 'Negative'.
Review: "This movie was a masterpiece. The acting was superb and the plot was thrilling." Sentiment: Positive
Review: "I was so bored I almost fell asleep. A complete waste of time." Sentiment: Negative
Review: "An incredible film with stunning visuals and a powerful story. Highly recommended!" Sentiment: Negative
Review: "I really enjoyed the clever dialogue and the surprising twists in the story." Sentiment:
What is the most likely reason the model is failing to provide an accurate classification for the final review?
Constructing a Few-Shot Prompt for Ticket Classification
A developer needs to use a large language model to classify incoming customer support tickets as 'Urgent' or 'Non-Urgent'. The goal is to achieve the highest possible accuracy for a new, unseen ticket. Which of the following prompt structures is best designed to guide the model toward the most reliable classification?