Google

A complete prompt for a large language model can be constructed by combining an explicit instruction with the input text and an output indicator. The instruction sets the context and defines the task, such as polarity classification with a specific set of labels. This is followed by the input to analyze, and finally, an indicator that signals where the model should provide its answer. For example: 'Assume that the polarity of a text is a label chosen from {positive, negative, neutral}. Identify the polarity of the input. Input: I love the food here. It's amazing! Polarity:'

Example of a Complete Prompt for Polarity Classification

You are tasked with using a large language model to categorize user feedback for a new mobile application. The feedback needs to be classified into one of three categories: 'Bug Report', 'Feature Request', or 'General Praise'. Write a complete, self-contained prompt that instructs the model to classify the following user feedback: 'The app crashes every time I try to upload a photo.'

Constructing a Classification Prompt

A data scientist needs to classify movie reviews into one of two categories: 'Recommended' or 'Not Recommended'. Which of the following prompts is best structured to ensure the language model consistently provides one of the desired labels for the input text?

A developer is creating a prompt to have a language model classify customer feedback. The model's outputs are inconsistent, sometimes generating long sentences instead of a simple category. Analyze the prompt below and identify the most critical missing component that is likely causing this issue.

**Prompt:**
```
Identify the sentiment of the following text.

Input: The user interface is confusing and difficult to navigate.
```

Learn Before

Related