Evaluating Prompt Strategy for a Creative RAG Task
A marketing team is using a system that retrieves successful advertising slogans to help a language model brainstorm new, creative slogans for a new product. The goal is to generate novel ideas inspired by, but not limited to, the retrieved examples. The system currently uses the following instruction for the language model: 'Based strictly on the provided examples, generate a new slogan.' Evaluate the effectiveness of this instruction for the team's goal. Explain why it is or is not suitable, and propose a specific revision to the instruction to better align with the desired creative outcome.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Evaluation in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Using Pre-trained Knowledge when Retrieved Context is Insufficient
Restricting LLM Answers to Provided Text
A team is developing a question-answering system for a company's internal, highly-accurate technical manuals. The system's highest priority is to ensure that all answers are strictly based on the information found within these manuals and to avoid generating any information from its general knowledge. Given a user's question and a relevant passage retrieved from the manuals, which of the following instructions to the language model would be most effective at achieving this goal?
Diagnosing and Correcting RAG System Output
Evaluating Prompt Strategy for a Creative RAG Task