Ethical Training: Using GenAI to Enhance Learning

What is generative AI?

Generative AI(GAI) is an artificial intelligence language model trained on a massive amount of text data that generates natural language responses in a natural conversation style. These systems use machine learning techniques, particularly deep learning, to identify and mimic patterns, styles, and structures found in the input data they are trained on. (Farrelly & Baker, 2023)

Text Generation: ChatGPT is a text generation tool that can create text based on the information you decide to input. This can be used to help students enhance their learning, brainstorm ideas, study, or review assignments and receive feedback.

Image Generation is an image generation tool that can create images based on the description you decide to input.

Code Generation – GenAI can generate and correct code.

Audio – TikTok is infamous for their videos using AI generated voices.

Video – Similar to Dall-E there is AI that can create video with a text description.

The coherent writing and hyper-realistic images that have captured public and business interest are examples of Generative AI models outputting data in ways once only possible with human thought, creativity, and effort. (Deloitte AI Institute, 2023) While we’re already in a world that relies heavily on technology – just think about the last time you went a day without your smartphone, the idea of using Gen AI can still be intimidating. People worry it may take over jobs and create a society that overly depends on technology.

Benefits of Generative AI for Students

Using generative AI as a student can help you in various ways. Not every student learns the same and not every student process’ information the same. This is where generative AI can equal the academic playing field. If you are reading a chapter and are not understanding the concept, you can bring it into a generative AI model and ask it to put the information in simple terms or explain the information like you’re in grade 5. Once you understand the fundamentals of the chapter you can use generative AI to test yourself by creating a practice quiz or flashcards to name a few.

Generative AI use goes even deeper if you are a student with a disability. If you do not have mobility of your hands or you don’t trust your eyesight the chat GPT TTS and VTT features are very advanced and user friendly. The TTS and VTT software that has been around for 20+ years does not have the realistic and human sounding voices that ChatGPT has. The biggest feedback I receive from students is they don’t like using the software because of robotic sounding voices. The ability to input course content into ChatGPT and have an engaging conversation, with the right prompts, about your course content is empowering and promotes independence for students.

The main benefit of using GenAI for learning is that you are saving our most valuable asset, time. From a student perspective one of the best things about GenAI is getting your course content tailored to your learning style in a way that customizes the information you’re learning and will present it in the most effective way. Using them for academics does not matter, what matters is learning and experience gained. (Yusuf, Pervin, & Román-González, 2024) Students who are using GenAI to customize their learning do not consider their use cheating. Their justification was that GenAI tools are just assistive technologies that provide academic assistance similar to other technological tools such as Google. (Yusuf, Pervin, & Román-González, 2024)

We as individuals and as a collective may well need to adopt a new pragmatic approach to how we live, work, teach, and study that recognizes the very real likelihood that GAI will become as ubiquitous as the internet itself in our everyday lives. (Farrelly & Baker, 2023)

Disadvantages of Generative AI for students

If you are not using generative AI with the goal of learning the content and would like it to create content without engaging in the process and being transparent about using generative AI this will negatively impact education and ability to be confident in your area of study. The most obvious disadvantages for students and instructors using generative AI is plagiarism.

Figure 1 (Yusuf, Pervin, & Román-González, 2024)

Even before the advent of ChatGPT, recent research reported that around 22% of students from an Austrian university admitted plagiarism. (Hopp & Speil, 2021) While plagiarism and AI are problematic students who want to circumvent academic responsibilities will find a way. However, there are many disadvantages to using generative AI that may be as obvious such as:

Privacy – Using AI tools often involves processing personal data. Students need to be aware about the data privacy policies of AI tools like ChatGPT, as there might be risks related to how their data is used and stored.

Misinformation – The information provided by GenAI may be outdated or incorrect. Fact checking should be done so students can be sure the information they’re using is accurate.

Socioeconomic – GenAI tools have premium versions, people who can afford to access these tools may have an unfair advantage over those who only use the free versions.

Regulations – Currently, there are no clear guidelines or standards on how o regulate the use of these tools or any other advanced AI technology. This leave the door open for unethical practices, including using AI for political propaganda, hate speech, and other harmful activities. (Luckett, 2023)

Lack of creativity – GenAI tools are designed to provide the most likely response based on patterns in the data they have been trained on. This can lead to standardized, predictable outputs that may not encourage original thinking.

Dependence – Relying on GenAI for answers to everything can lead to a dependency which can impact a students’ ability to solve problems and think critically independently.

Bias – AI; it is not a neutral and objective ‘entity’; it depends on the quality of the data used in training, and the method of refining or tuning the model, which can be subject to the human biases of their creators (Farrelly & Baker, 2023)

Ethical Concerns and Academic Integrity – The ethical concern for the use of GenAI in academic settings, particularly around the authenticity of the work submitted. Students might submit AI-generated content as their own, which can raise issues of plagiarism and academic dishonesty.

Ethical use of Generative AI is not meant to circumvent academic responsibilities but to customize and enhance education. One of the most significant challenges associated with these AI tools is their potential misuse. (Luckett, 2023)

These disadvantages are concerning but if we teach students the fundamentals of generative AI and how to ethically use it we can develop AI literacy and empower students to make their own choices.

Critical AI Literacy

The notion of literacy has more recently been applied to defining skill sets in a variety of disciplines that have the same potential to enable expression, communication, and access to knowledge. (Long & Magerko, 2020) For example digital literacy empowers individuals to navigate and utilize digital technologies effectively to deepen their understanding of digital tools and platforms. Similarly, AI literacy equips people with the knowledge and skills necessary to comprehend, engage with, and critically evaluate information generated by AI tools. By defining and understanding AI literacy, we can ensure that people are not only consuming AI technologies but also informed participants who can question the information and be aware of the potential risks involved.

Critical AI literacy encompasses the ability to verify the integrity of the AI-generated content, identify when content is produced by AI, and understand the language and practices for responsible and effective AI usage. It includes the skills to integrate AI into daily life with an awareness of its limitations and impacts and a deeper understanding of AI’s influential capabilities. Critical AI literacy also addresses the social and ethical implications, safety, privacy, and legal considerations associated with AI. It involves recognizing biases and misinformation, knowing when and when not to use AI, and being fully aware of the risks and harms that come with it. Ultimately, it calls for conscientious, responsible, and ethical use of AI, encouraging critical thinking and appropriate application without avoidance. (Aspenlieder, 2024)

There is a need for AI literacy in education, Gen AI is ubiquitous and will continue to grow and be built-in to software and devices. Students should develop an understanding of AI literacy and be trained on how to use it ethically. Students are taught how to use assistive programs and devices and once the training is complete it is their choice whether they continue to use technologies to improve their productivity, efficiency, and enhance their understanding of information. The job of institutions is not to restrict Gen AI, it’s to teach students how to ethically use these tools and the potential risks that come with them. As such, students should be equipped with the competencies needed to thrive in the workplace. Moreover, ensuring that all students have access to and can benefit from emerging technologies helps reduce inequalities in educational and professional opportunities while creating a more level playing field and promoting social equity. (Dai, Liu & Lim, 2023)

There are instructors who do not allow the use of generative AI and state that in the syllabus or learning plan. Should instructors embrace AI literacy and create an awareness that fosters transparency? Tyton Partners did a survey “If your instructor or institution prohibits the use of generative AI writing tools, how likely are you to still use something like ChatGPT?”.

Developing Generative AI literacy

The necessity to develop AI literacy is crucial for empowering people to make informed decisions if they choose to use generative AI. This includes providing training and education to individuals and organizations on the responsible use and development of AI, as well as increasing public awareness about AI and its potential impacts on society. (Luckett, 2023)

Figure 2 (Yusuf, Pervin, & Román-González, 2024)

Using generative AI is easier than you think. Here’s how you can get started and make the most of this powerful technology:

1. Start with simple questions
2. Begin by asking AI about the specific tasks you want to accomplish. For instance, if you need help with an assignment, simply ask, “How can you help me with this assignment?” You’ll be surprised at how AI can guide you through various steps.
3. Explore AI concepts through inquiry
4.  To understand AI better, ask it directly. Questions like “What is AI?” or “How does AI work?” can get you started. Dive deeper by exploring key terms such as machine learning, deep learning, and neural networks. The more you ask, the more you learn!
5. Question the answers AI gives you and ask it to help you develop critical thinking about the topic you’re talking about.
6. Leverage Familiar Tools, if you’ve ever used Siri, Alexa, or any chatbot, you already have some hands-on experience with AI. Use these interactions to build your confidence and curiosity about what AI can do.
7. Interactive Learning
8. Engage and Experiment: Don’t hesitate to experiment with different types of questions and tasks. Whether it’s brainstorming ideas, organizing notes, or creating study aids, let AI be your interactive learning partner.

By engaging with AI in these ways, you’ll develop a strong foundation in AI literacy, empowering you to leverage technology effectively for your academic success and unlock the potential for a custom learning experience. If our aim is to equip our students with skills, knowledge, and competencies that will allow them to thrive in the 21^st century, we need to rapidly adapt our programming to include AI literacy and competency across the disciplines. Academics and staff in universities need to develop literacy in the applications of AI to their own disciplines. (Farrelly & Baker, 2023)

Unlock Your Potential with Generative AI Literacy

In today’s fast-paced world, the ability to harness the power of generative AI can enhance your learning and creativity. Imagine having a tool that not only helps you brainstorm ideas but also assists you with note-taking, creates practice tests, and synthesizes complex information into understandable insights. Developing AI literacy opens up a world of possibilities, making your academic journey personalized and more engaging. The essence of all technologies is for students to learn as far as the goal will be achieved…I see no harm in it because we are in a digital era where technology serves as assistive tools for self-learning and development. (Yusuf, Pervin, & Román-González, 2024)

Brainstorm ideas – Sometimes something as simple as a topic or a slide title can stop the creative process from flowing. Having the ability to discuss ideas with a tool like ChatGPT can keep the ideas flowing and assist in finding and attaining the vision you have.

Note-taking – Taking notes is difficult, organizing the notes can be even harder. With ChatGPT you can input specific prompts to have ChatGPT act as a copyright and a university student who likes detailed notes with headings, subheadings and bullet points, you can even ask ChatGPT to take out redundant information or simplify information that is not in your language.

Practice Tests – Once you have put your notes into ChatGPT you can now be quizzed in any way you would like by specifying how you would like to be assessed e.g.; multiple choice, true or false. You can also ask GenAI to create a practice test and give you the explanation for each answer. This technique may help with test anxiety.

Synthesizing Info – With GenAI you are able to summarize large amounts of content in a concise way. If the content is still not connecting you can also ask GenAI to explain that in metaphors of your favourite activity, show, movie, sport, book etc…

Learning and Research – GenAI will answer the questions about the content you input instantly. This is helpful because you do not have to wait for a response that may or may not answer your question. You can ask questions until you receive the answer in an interactive way. Due to the conversational style of ChatGPT you can even ask what questions I should ask to get better at X,Y,Z and it will give you suggestions.

Instant Feedback – You can input your work and rubric into ChatGPT and it will generate instant feedback. With this immediate feedback, students can clarify their confusion and resolve misconceptions in real time as well as apply new understanding to subsequent tasks. Therefore, the immediate feedback of ChatGPT is likely to enhance student learning engagement and increase the efficiency of education. (Dai, Liu, & Lim, 2023)

Personalised Learning – GenAI, specifically ChatGPT can personalise information you input and act as a collaborator. It can serve as a supplementary resource to answer students’ questions, provide explanations, and offer additional learning opportunities tailored to students’ needs. (Dai, Liu, & Lim, 2023)

By embracing generative AI literacy, you’ll unlock a powerful toolset that enhances your learning experience, making you more efficient, creative, and prepared for your academic challenges. One of the main advantages of AI is the conversational style of communication enabled students to feel like they are naturally collaborating and engaging with their content and learning on their own time. This is especially useful for students who are unable to attend classes due to physical or mental health issues. (Barber et al., 2021)

Ethical Use of Generative AI

Ethics in AI involves guiding the development and use of AI technologies to be fair, transparent, and beneficial for all. It focuses on preventing bias, respecting privacy, promoting safety, and ensuring inclusivity. The goal is to enhance human capabilities and positively contribute to society without undermining human values or rights. It aims to ensure that people, processes, and organization that engineer AI assume responsibility and are engineered ethically in line with moral codes and principles. (Müller, 2023)

Privacy – Ensure personal data is protected when using AI tools.

Bias and Fairness – Be aware of potential biases in AI generated content.

Transparency – Clearly indicate when content is generated by AI.

Integrity – Using GenAI in academic setting involves adhering to ethical standards and principles that ensure honesty, fairness, and responsibility.

If you’re going to use generative AI you should have an understanding of how to ethically use it as a tool to enhance your learning, develop your understanding of information and build critical thinking skills. Users should familiarize themselves with issues regarding algorithm transparency, data ownership, privacy, hidden labor, embedded bias, and undisclosed plagiarism. (Farrelly & Baker, 2023) Ensuring integrity when using AI involved a commitment to transparency, ethical use, and critical engagement. By following these principles, and incorporating best practices students can fully utilize the benefits of AI while maintain academic integrity and ethical standards.

Best Practices

Understanding the basics of generative AI and the capabilities and current limitations and risks you can familiarize yourself with your tool of choice. Identify your goal for your session, for example; brainstorming, generating ideas, or receiving feedback, establishing a clear purpose will help you create your prompts. The more specific you are the more useful your response will be. Gen AI is not always correct and can produce contradictory responses, it is crucial to verify information outputted.

Transparency: Mention any AI assistance in your assignments to maintain academic integrity.

Avoid Plagiarism: Modify and integrate content into your original thoughts, copying and pasting AI-generated text can lead to plagiarism.

Respect Privacy: Be mindful of privacy when using AI tools. Avoid entering personal or sensitive information, as data handling may not be secure.

Use Responsibly: Consider the ethical implications of AI use, especially in competitive settings like exams, and the broader impact of relying on AI in education.

Develop Critical Thinking: Use AI interactions to enhance critical thinking. Question AI responses, explore their reasoning, and compare them with established knowledge.

Start Small: Use AI for brainstorming or drafting but do your own research and writing.

Verify Content: Cross-check information generated by AI with reliable sources.

By following these best practices, students can ethically use AI tools like ChatGPT to support their education while maintaining academic integrity and fostering intellectual growth. The future use of GenAI in higher education continues to grow and more students and instructors are likely to be curious of how it can impact their daily lives.

Figure 3 (Yusuf, Pervin, & Román-González, 2024)

Prompt Engineering

Teaching people how to write prompts or finding prompts you have written yourself for a specific reason can be used to enhance learning and deepen your understanding, critical thinking, and accelerate the writing process. You can also ask Gen AI to give you some examples of prompts generated by giving Chat GPT this prompt.

Prompt:

You are a prompt engineer who works at a university. You are giving a lecture on best practices for ethical AI use. What are some of the best prompts to help students to enhance their learning?

Response:

As a prompt engineer lecturing on best practices for ethical AI use, you can design prompts that not only engage students but also deepen their understanding of ethical considerations in AI. Here are some thoughtfully crafted prompts that could help enhance learning in this area:

These prompts are designed to encourage critical thinking, ethical reasoning, and multidimensional analysis of AI technologies. They require students to engage with the material actively, applying ethical principles to real and hypothetical situations, and considering the broad societal impacts of AI.

If you use GenAI ethically you can work on critical thinking and explore different perspectives. The prompts it generated want you to engage with your content and consider the implications and ethics of using gen AI.

Limitations and Risks of Generative AI

Since its inception, the integration of GenAI into education has garnered significant attention. (Yusuf, Pervin, & Román-González, 2024) The potential benefits and concerns associated with GenAI in the classroom have been explored by various researchers, shedding light on its transformative potential and challenges. The limitations and risks of generative AI are still being considered due to the limitless ways we integrate Gen ai in our daily lives.

Privacy  – AI systems collect and process large amounts of data. This data could be used to invade people’s privacy. For example, AI systems could collect information about people’s online activity and use it in ways that violate the individual’s privacy. (Luckett, 2023)

Safety – AI systems are complex and can be difficult to understand. This makes it difficult to ensure that they are safe for use. For example, AI systems used in self-driving cars could make mistakes that could lead to accidents. (Luckett, 2023)

Academic Integrity – Using AI to create content without proper citation can be considered plagiarism.

Misinformation – AI may give biased or inaccurate information depending on the data it has been trained on.

Over-reliance – Dependence on AI can impact the development of critical thinking skills.

Accountability – A significant risk because it raises questions about responsibility, especially when AI systems make life-altering decisions in critical areas such as healthcare, criminal justice, finance, and autonomous vehicles.

Bias – Algorithmic bias is often directly related to the bias present in training datasets. Agents in-the-wild are also able to learn bias and bigotry from human users. (Neff & Nagy, 2016)

Circumventing Academic Responsibilities – AI is subject to misuse and there are currently no accurate detection tools. If students choose to bypass their learning by using AI to create content for them they may face consequences of academic dishonesty or expulsion.

Devaluation of Education – Using Gen AI to bypass academic responsibilities undermines the very purpose of higher education, which is to challenge and education students, and could ultimately lead to a devaluation of degrees (Debby R. E. Cotton Chatting and cheating)

To address these concerns regulations must be developed to ensure that AI is developed and used ethically and responsibly. (Luckett, 2023) The limitations and risks AI poses can be mitigated with proper legal frameworks and cultivating an awareness on the AI literacy and ethical use.

Generative AI Governance

To govern the use on generative AI in higher education effectively, institutions can create comprehensive AI governance policies that emphasize ethical use, transparency, accountability, and security. If institutions can create an environment where students, faculty, staff, and stakeholders have a say in the role of Gen AI in academic settings we can democratize the use of Gen AI tools.

Framework and Guidelines

EU AI Act: Provides a comprehensive regulatory framework for AI, emphasizing risk-based regulation and ethical use.

NIST AI Risk Management Framework: Offers guidelines for managing risks associated with AI technologies, focusing on trustworthiness and fairness.

Singapore’s AI Governance Model: Emphasizes the importance of transparency, accountability, and collaboration in AI governance.

Google AI Principles: Highlights the need for ethical AI development and deployment, focusing on fairness, privacy, and security.

By implementing these AI governance policies, higher education institutions can ensure that generative AI is used ethically, responsibly, and effectively, fostering a positive and equitable academic environment.

Resources

Aspenlieder, E. 2024. Critical Literacies, Misinformation and Deepfakes [PowerPoint]. Inspire 3EL3. McMaster. May 28, 2024.

Farrelly, T., & Baker, N. (2023). Generative Artificial Intelligence: Implications and Considerations for Higher Education Practice. Education Sciences, 13(11), 1109. https://doi.org/10.3390/educsci13111109

Dai, Y., Liu, A., & Lim, C. P. (2023). Reconceptualizing ChatGPT and generative AI as a student-driven innovation in higher education. In Proceedings of the 33rd CIRP Design Conference. Department of Curriculum and Instruction, The Chinese University of Hong Kong, Hong Kong SAR, China; School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia; Faculty of Education and Human Development, The Education University of Hong Kong, Hong Kong SAR, China.

Ka Yuk Chan, Cecelia. “Students’ voices on generative AI: perceptions, benefits, and challenges in higher education”. International Journal of Educational Technology in Higher Education 43 (2023).

Long, D., & Magerko, B. (2020). What is AI literacy? Competencies and design considerations. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (pp. 1–16). https://doi.org/10.1145/3313831.3376727

Müller, V. C. (2023). Ethics of artificial intelligence and robotics. In E. N. Zalta & U. Nodelman (Eds.), The Stanford Encyclopedia of Philosophy (Fall 2023 ed.). Stanford University. https://plato.stanford.edu/archives/fall2023/entries/ethics-ai/

KPMG. “Despite popularity, six in 10 students consider generative AI cheating” KPMG, August 30, 2023.

Buszka, Sarah, Jeremy Cortez, and Isabella Meltzer. “Students’ Perspectives on Using AI”. Educause, September 6, 2023.

Yusuf, A., Pervin, N. & Román-González, M. Generative AI and the future of higher education: a threat to academic integrity or reformation? Evidence from multicultural perspectives. Int J Educ Technol High Educ 21, 21 (2024). https://doi.org/10.1186/s41239-024-00453-6

Liu, Danny, and Adam Bridgeman. “Students answer your questions about generative AI part 1: Assessments and their future”. Teaching@Sydney, March 13, 2023.

Liu, Danny, and Adam Bridgeman. “Students answer your questions about generative AI part 2: Ethics, integrity, and the value of university”. Teaching@Sydney, March 13, 2023.

Barber, M., Bird, L., Fleming, J., Titterington-Giles, E., Edwards, E., & Leyland, C. (2021). Gravity assist: Propelling higher education towards a brighter future. Office for Students. Retrieved from https://www.officeforstudents.org.uk/publications/gravity-assist-propelling-higher-education-towards-a-brighter-future/f

Luckett, J. (2023). Regulating generative AI: A pathway to ethical and responsible implementation. International Journal on Cybernetics & Informatics.

Neff, G., & Nagy, P. (2016). Talking to bots: Symbiotic agency and the case of Tay. In Automation, Algorithms, and Politics.

Deloitte AI Institute. (2023). The Government & Public Services Generative AI Dossier: A selection of high-impact use cases. Deloitte. Retrieved from https://www.deloitte.com/us/generative-ai-dossier

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.