Improving a Prompt for Event Extraction
An AI developer is using a large language model to extract key events from news articles. They use the following instruction within their prompt: Your task is to find all the actions in the text. When given a sentence like, 'The president signed the bill into law after walking into the room,' the model extracts both 'president signed the bill' and 'president walking into the room.' Analyze why the developer's instruction is not ideal for extracting only the most significant occurrences. Then, propose a more effective instruction.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Computing Sciences
Foundations of Large Language Models Course
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
An AI engineer is constructing a prompt to guide a large language model. The prompt follows this structure:
You will be provided with a document. Your task is to {task-description}.The document is:
On Tuesday, a major earthquake struck the coastal region, leading to the immediate evacuation of several towns. Emergency services were deployed by the government later that day.Which of the following options would be the most effective
{task-description}to specifically extract the key occurrences from the document?Improving a Prompt for Event Extraction
Crafting a Task Description for Event Extraction