Prompts are the instructions used to ask a large language model (LLM) to perform a task and create an output. The more specific instructions you can give the generative AI, the better output you're going to get. Prompting generative AI each step of the way guides it to ensure consistency and keeps the AI on topic.
The CLEAR Framework for Prompt Engineering was created by Dr. Leo S. Lo of the University of New Mexico to optimize interaction with generative AI. Each letter in the CLEAR acronym stands for a step in making prompts:
1. Concise - A concise prompt removes superfluous information, allowing AI language models to focus on the most important aspects of the task. Example: Instead of requesting, "Please provide me with an extensive discussion on the factors that contributed to the economic growth of China during the last few decades," use a concise prompt like, "Identify factors behind China's recent economic growth."
2. Logical - To create a logical prompt, ensure that the provided information follows a natural progression and that the relationships between concepts are evident. Example: "List the steps to write a research paper, beginning with selecting a topic and ending with proofreading the final draft."
3. Explicit - Include specifics about the type of information you seek and how it should be conveyed to make a prompt explicit. Example: Instead of, "Tell me about the French Revolution," an explicit prompt would be, "Provide a concise overview of the French Revolution, emphasizing its causes, major events, and consequences."
4. Adaptive - When crafting adaptive prompts, be flexible and willing to attempt new approaches based on the performance of the AI model. Example: If asking, "What are some ways to conserve water?" leads to generic responses, try a more targeted and adaptive prompt like, "List household practices for conserving water and their potential impact."
5. Reflective - Reflective prompts emphasize the significance of continuous evaluation in enhancing prompt engineering techniques. Example: After receiving AI-generated content on the benefits of a plant-based diet, evaluate the response's accuracy, relevance, and completeness. Use insights from the evaluation to refine prompts, such as asking for more specific benefits or focusing on certain aspects of a plant-based diet.
Source:
Lo, L.S. (2023). The CLEAR path: A framework for enhancing information literacy through prompt engineering. The Journal of Academic Librarianship, 49(4), 1-3. https://doi.org/10.1016/j.acalib.2023.102720
Words to include for performing specific tasks:
To ask specific questions:
https://www.sanjac.edu/library| Central Library: 281-476-1850 | Generation Park Campus: 281-998-6350 x8133 | North Library: 281-459-7116 | South Library: 281-998-6350 ext. 3306