Leo Lo, Dean of the College of University Libraries at The University of New Mexico, has created a guide on assessing Generative AI prompts called the CLEAR Framework.
CLEAR Dimensions |
Examples |
Concise Brevity and clarity are essential. Avoid unnecessary details, ensuring focus on the main topic. |
Instead of: 'Can you provide a detailed explanation of the process of photosynthesis and its significance?' (verbose) |
Logical Ensure a logical structure and flow of ideas within the prompt. |
Instead of: 'How do I write a research paper?' (unclear structure) |
Explicit Provide clear output specifications. Specify format, scope, and content explicitly. |
Example: 'Identify five renewable energy sources and explain how each works.' (explicit) Instead of: 'What are renewable energy sources?' (vague) |
Adaptive Prompts should be adaptable. Flexibility allows for customization based on responses. |
Example: 'Examine the relationship between social media usage and anxiety in adolescents.' (adaptive) Instead of: 'Discuss social media's impact on mental health.' (too general) |
Reflective Continuous evaluation of prompts for improvement based on outcomes. |
Example: After receiving content on the benefits of a plant-based diet, refine the prompt to focus on specific benefits or dietary aspects. Instead of: Accepting broad, less relevant responses without reflection. |
You can learn more about the framework by reading the article: Lo, L. S. (2023). The CLEAR Path: A Framework for Enhancing Information Literacy Through Prompt Engineering. The Journal of Academic Librarianship, 49(4), 102720–. https://doi.org/10.1016/j.acalib.2023.102720