Generative AI Prompt Engineering for Educators: Practical Strategies

被引:1
|
作者
Park, Jiyeon [1 ]
Choo, Sam [2 ]
机构
[1] Eastern Kentucky Univ, Dept Teaching Learning & Educ Leadership, 521 Lancaster Ave, Richmond, KY 40475 USA
[2] Univ Minnesota, Dept Educ Psychol, Minneapolis, MN USA
关键词
prompt engineering; artificial intelligence; generative AI;
D O I
10.1177/01626434241298954
中图分类号
G76 [特殊教育];
学科分类号
040109 ;
摘要
Generative AI, such as ChatGPT, produces personalized and contextually relevant content based on user prompts (inputs provided by users). These prompts act as the primary form of interaction between users and AI models, making their quality essential for generating the most relevant outputs. The process of writing, refining, and optimizing prompts, known as prompt engineering, is key to obtaining high-quality desired outputs from generative AI. For educators, proficiency in prompt engineering is crucial for effective interaction with AI as it enhances efficiency and produces the most relevant information. In this paper, we introduce practical strategies for prompt engineering for educators: (a) include essential components, including Persona, Aim, Recipients, Theme, and Structure (PARTS); (b) develop prompts using Concise, Logical, Explicit, Adaptive, and Restrictive (CLEAR) languages; (c) evaluate output and refine prompts: Rephrase key words, Experiment with context and examples, Feedback loop, Inquiry questions, Navigate by iterations, Evaluate and verify outputs (REFINE); and (d) apply with accountability. Examples for special educators and online resources are included.
引用
收藏
页数:7
相关论文
共 50 条
  • [31] Generative AI Applications and Tools in Engineering Education
    Stankovski, Stevan
    Ostojic, Gordana
    Tegeltija, Srdan
    Stanojevic, Milos
    Babic, Mladen
    Zhang, Xiaoshuan
    2024 23RD INTERNATIONAL SYMPOSIUM INFOTEH-JAHORINA, INFOTEH, 2024,
  • [32] Rational enzyme engineering via generative AI
    Xie, Wenjun
    BIOPHYSICAL JOURNAL, 2024, 123 (03) : 58A - 58A
  • [33] Responsible use of Generative AI in chemical engineering
    Daniel, Thorin
    Xuan, Jin
    DIGITAL CHEMICAL ENGINEERING, 2024, 12
  • [34] Generative AI in the Wild: Prospects, Challenges, and Strategies
    Sun, Yuan
    Jang, Eunchae
    Ma, Fenglong
    Wang, Ting
    PROCEEDINGS OF THE 2024 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYTEMS, CHI 2024, 2024,
  • [35] Generative Artificial Intelligence and Prompt Engineering: A Primer for Orthopaedic Surgeons
    Carroll, Amber N.
    Storms, Lewis A.
    Malempati, Chaitu
    Shanavas, Ridah V.
    Badarudeen, Sameer
    JBJS REVIEWS, 2024, 12 (10)
  • [36] Generating Employable, Intelligent Graduates in a World With Generative AI: Thoughts for Educators
    Bowles, Devin C.
    Kruger, Jessica Sloan
    PEDAGOGY IN HEALTH PROMOTION, 2023, 9 (02) : 75 - 77
  • [37] Prompt Aloud!: Incorporating image-generative AI into STEAM class with learning analytics using prompt data
    Lee, Unggi
    Han, Ariel
    Lee, Jeongjin
    Lee, Eunseo
    Kim, Jiwon
    Kim, Hyeoncheol
    Lim, Cheolil
    EDUCATION AND INFORMATION TECHNOLOGIES, 2024, 29 (08) : 9575 - 9605
  • [38] Speeding Up the Engineering of Interactive Systems with Generative AI
    Schmidt, Albrecht
    COMPANION OF THE 2023 ACM SIGCHI SYMPOSIUM ON ENGINEERING INTERACTIVE COMPUTING SYSTEMS, EICS 2023, 2023, : 7 - 8
  • [39] Navigating the Complexity of Generative AI Adoption in Software Engineering
    Russo, Daniel
    ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2024, 33 (05)
  • [40] Generative AI and process systems engineering: The next frontier
    Decardi-Nelson, Benjamin
    Alshehri, Abdulelah S.
    Ajagekar, Akshay
    You, Fengqi
    COMPUTERS & CHEMICAL ENGINEERING, 2024, 187