Example of an Instruction for LLM-based Prompt Generation

A team is tasked with creating a system to summarize legal documents. To begin, they write a detailed, two-page description of the desired summary format, key information to include, and the target audience. They then input this description into a large language model with the instruction: 'Based on the provided document, generate a set of effective prompts for a summarization task.' When critiquing this team's strategy for creating an initial set of prompts, what is the most critical factor that will determine the success of their approach?

Troubleshooting Initial Prompt Generation

Evaluating a Prompt Generation Strategy