Learn Before
An experienced team of prompt engineers is tasked with creating prompts for a novel scientific summarization task. After weeks of crafting detailed, logically structured prompts based on their best practices, they find performance is mediocre. In a final attempt, they test a series of structurally unusual and counter-intuitive prompts, one of which dramatically outperforms all their previous efforts. Which limitation of manual prompt design does this scenario most clearly illustrate?
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Diagnosing a Prompt Engineering Plateau
An experienced team of prompt engineers is tasked with creating prompts for a novel scientific summarization task. After weeks of crafting detailed, logically structured prompts based on their best practices, they find performance is mediocre. In a final attempt, they test a series of structurally unusual and counter-intuitive prompts, one of which dramatically outperforms all their previous efforts. Which limitation of manual prompt design does this scenario most clearly illustrate?
Critique of Expertise-Driven Prompt Engineering