Generative AI tools create new content based on what they learn from their database(s). To make use of these tools, understanding how they work can improve how you and your students use them, or prompt them. We’ll explain ChatGPT as an example, below.
Though sometimes used interchangeably, ChatGPT and GPT are actually different pieces of technology. Built by the same research company, Open AI, the interactive chatbot app we know and use is ChatGPT. This chat platform is powered by GPT, a Large Language Model. Large Language Model (or LLM) refers to the technology that drives Natural Language Processing chatbots like ChatGPT, Bard, and Bing. LLMs “are trained on massive amounts of information scraped from the internet” and are designed to predict words based on likelihood, and cannot necessarily distinguish true information from predicted word sequences (Reidl 2023).
LLMs often “hallucinate” or offer information that isn’t true, nor can it be cited (Weise and Metz, 2023). But GPT models are continuously being improved. For example, while the industry standard is still GPT-3, newer versions such as GPT-4 will continue to be developed (Alston 2023).
Flowchart adapted from the original created by: Aleksandr Tiulkanov (January 2023) in ChatGPTand Artificial Intelligence in Higher Education: Quick Start Guide. UNESCO. https://unesdoc.unesco.org/ark:/48223/pf0000385146.
Despite the tendency to hallucinate, text-based AI tools can still be extremely useful, if they’re prompted appropriately. "Prompting" in the context of AI refers to the specific language entered into a chatbot platform like ChatGPT. Also called “prompt engineering,” teaching students to skillfully craft input into an AI tool can help them learn how to ask useful questions of AI. (To explore more on prompt engineering, see Alby 2023, Chen 2023, Huang 2023, Riedl 2023, Saravia 2023, and Weise and Metz 2023.)
Below, we include a list of AI tools grouped by which learning activity you'd like your students to do; each of which have unique prompting specificities.
AI tool by activity
- Idea Generation: ChatGPT, Gemini, Bing, Claude, IdeaNote
- Concept Mapping & Planning: Lucidchart
- Time/Project Management: krisp.ai/ai-meeting-assistant, Goblin Tools, Trello, Asana
- Research Exploration & Literature Review: typeset.io, Rayyan, Explainpaper, Connectedpapers, Research Rabbit, Scite, Perplexity, Semantic Scholar
- Summarizing: Glasp, ChatGPT, Gemini, Bing, Claude, Smmry
- Outlining & Drafting: ChatGPT, Gemini, Bing, Claude, Kickresume, textblaze.me, Scrivener
- Collaborative Writing: Overleaf, Google Docs, Authorea, Manuscripts.io
- Reference Management: Zotero, Mendeley, EndNote, Citavi
- Coding Help: hashnode.com/ai, Fronty, Tabnine, debugcode.ai, Stack Overflow
- Data Analysis & Statistical Analysis: GPT4,Tableau AI, Excel, Google Workspace (non-GU), Power.bi, Rstudio (tidyverse), (tools work with: SPSS, SAS, Stata, Python (pandas, NumPy)
- Data Visualization: D3.js, Plotly, Infogram, Datawrapper, Adobe Illustrator
- Presentation Tools: Gamma, SlidesGPT, slidesgo, Canva, Prezi
Platform/application summaries
- Research Rabbit - Research Rabbit is a free online citation-based literature mapping tool that helps explore research by visually mapping out related articles and authors based on your starting point (seed papers).
- Connected Papers - Another free literature visualization tool that helps discover new research and track the development of a field. It focuses on the relationships between different papers rather than just the citations.
- Phind - A search engine specifically designed for academic research that can search across a variety of different databases and sources and uses machine learning to help you find the most relevant results.
- Chat PDF - Allows you to have a conversation with a computer about the content of a PDF document and can be useful for summarizing the document, finding specific information, or getting different perspectives on the material.
- Academic Insight Lab - A collection of tools and resources designed to help researchers with different aspects of their work, such as writing, publishing, and data analysis.
- Consensus - A platform that helps researchers collaborate and share their work; allows you to create private groups, share documents, and have discussions with other researchers.
- Magic School - Helps you learn about new research by watching short videos created by other researchers ad can be a great way to get a quick overview of a topic or to find new research that you might be interested in.
- Perplexity - Helps you understand the language used in academic research papers and can identify key terms, phrases, and concepts, and it can also show you how these terms are used in different contexts.
- Scite - Allows you to read and discuss academic research papers in real time with other researchers and can be a great way to get feedback on your work or to learn more about a topic from other experts.
- Keenious - Helps researchers find and manage their research data as well as store, organize, and share data with others.
- Elicit - Helps write better research papers and also provides feedback on your writing style, grammar, and clarity.
CNDLS resources
Guides
Presentations and events
AI workshop series
- Introduction to AI | February 2, 2024 [Slides]
- AI Prompt Design: Brainstorming and Creativity | February 9, 2024 [Slides]
- Simulations & Case Studies: Using AI as a Thought Partner | Feb. 16, 2024 [Slides]
- Teaching with AI: Tools and Techniques | Feb. 29, 2024 [Slides]
- How to Use AI for Research and Data Analysis | March 14, 2024 [Slides]
What We're Learning About Learning podcast episodes
Contact CNDLS for a consultation on working with AI in your classroom.
Resources by discipline
How might generative AI impact teaching and learning in your discipline, in particular? Browse the list of resources below, which capture discipline-specific approaches to addressing the use of AI tools in the classroom.
Note the following research tools can be used across disciplines:
Writing
Second language learning
Humanities
Science, Technology, Engineering, and Math (STEM)
- Brett A. Becker, et al. (2023). Programming Is Hard - Or at Least It Used to Be: Educational Opportunities and Challenges of AI Code Generation. In Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1 (Toronto ON, Canada) (SIGCSE 2023). Association for Computing Machinery, New York, NY, USA, 500--506.
- Korinek, Anton. (February 2023). Language Models and Cognitive Automation for Economic Research. National Bureau of Economic Research. 10.3386/w30957.
- Kortemeyer, G. (2023). Can an AI-tool grade assignments in an introductory physics course?. arXiv.
- Masters, Ken. (2023) Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide No. 158, Medical Teacher, 45:6, 574-584.
- Wei, Y. (2023). Repilot: iSE-UIUC. https://github.com/ise-uiuc/Repilot (Original work published 2022).
References
Alston, E. (2023) "ChatGPT vs. GPT-3 and GPT-4: What's the difference?" Zapier.
Chen, Brian X. (May 2023). “Get the Best from ChatGPT with these golden prompts.” New York Times.
Huang, P. (June 2023). ChatGPT Cheat Sheet. The Neuron.
Riedl, A. (2023). A Very Gentle Introduction to Large Language Models without the Hype. Medium.
Saravia, E. (2022). Prompt Engineering Guide. Democratizing Artificial Intelligence Research, Education, and Technologies.
Weise, K. and Metz C. (2023). When A.I. Chatbots Hallucinate. The New York Times.