A news organization wants to use a language model to automatically sort its articles. The required categories are 'Politics', 'Technology', 'Sports', and 'Entertainment'. Write a complete and effective prompt that instructs the model to classify a given news article into one of these four categories.

Google

A prompt for a classification task is a specific instruction given to a language model to categorize a given piece of text into one of several predefined classes. This directs the model to perform a sorting or labeling function rather than generating new text or extracting information.

Prompt for a Classification Task

An example of a prompt for a classification task is instructing a model to identify spam. The prompt might be structured as: 'Classify the following email as spam or not spam. Text: Congratulations! You’ve won a \$500 gift card. Click here to claim now.' The model's task is to assign either the 'spam' or 'not spam' label to the provided text.

Example of a Spam Classification Prompt

A developer needs to use a language model to automatically sort customer feedback into three categories: 'Positive', 'Negative', or 'Neutral'. Which of the following instructions would be most effective for this specific goal?

Critique the team's current instruction based on the scenario provided. Explain why it is not well-suited for their goal and propose a more effective instruction that would reliably sort the emails into the required categories.

Evaluating a Prompt for Support Ticket Routing

Crafting a Prompt for News Article Categorization

A common text classification task involves determining whether an email is spam. For example, a message with the text, "Congratulations! You’ve won a \$500 gift card. Click here to claim now," would be presented as an item to be classified as either spam or not spam.

Learn Before

Related