Google

An instruction-based prompt is structured with key components to guide a large language model. It typically begins with a task description that outlines the objective, such as defining the task and the set of possible labels. It also uses indicators, like 'Input' and 'Polarity', to clearly demarcate the provided text and to signal where the output should be placed. The model is then expected to generate the correct label as a text completion that follows the output indicator.

Components of an Instruction-based Prompt

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

A user wants a language model to categorize customer feedback into one of three categories: 'Positive', 'Negative', or 'Neutral'. They provide the model with the following text:

`Input: The checkout process was confusing and took too long.`

The model's responses are inconsistent, sometimes generating a long paragraph instead of a single category label. Based on the typical structure of an effective instruction-based prompt, identify two key components that are missing and explain how their absence causes the inconsistent output.

Analyzing a Flawed Prompt

A user is trying to get a large language model to summarize news articles. They are using the prompt below but find that the model sometimes provides a very long summary, sometimes just a single sentence, and occasionally adds its own opinions. Based on your understanding of prompt components, analyze the user's prompt and explain which specific components are missing or poorly defined, and how improving them would lead to more consistent and accurate summaries.

Improving Prompt Structure for Better LLM Outputs

A user provides the following text to a large language model:

`Classify the sentiment of the following movie review. The sentiment can be one of {positive, negative}.

Review: "This film was a masterpiece of storytelling and cinematography."
Sentiment:`

Which of the following options correctly breaks down the components of this prompt and their respective functions?

Learn Before

Related