Engaging with AI in your education and assessment

First of a series of student briefings from the expert AI and education group with guidance on how you might engage with this in your assessments effectively and ethically. Published February 2023.

There is a lot of interest in and experimentation with artificial intelligence (AI) tools such as ChatGPT, DALLE-2, CoPilot, and most recently Google Bard. 

All of these can be helpful tools for generating content that might contribute to assessed work, which has led some institutions to prohibit their use.

We believe these tools are potentially transformative as well as disruptive, that they will feature in many academic and professional workplaces, and that rather than seek to prohibit your use of them, we will support you in using them effectively, ethically and transparently.  

Whilst they are attractively powerful and easy to use, they can also provide misleading or incorrect information, and can negatively impact your learning as they can offer shortcuts that reduce the need for critical engagement that is key to deep and meaningful learning. You also need to be aware of the difference between reasonable use of such tools, and at what point their use might be regarded as giving you an unfair advantage.  

What is AI good for? 

These tools can help students in a number of ways – for instance 

• Answering questions where answers are based on material which can be found on the internet. 
• Drafting ideas and planning or structuring written materials. 
• Generating ideas for graphics, images and visuals. 
• Reviewing and critically analysing written materials to assess their validity. 
• Helping to improve your grammar and writing structure – especially helpful if English is a second language. 
• Experimenting with different writing styles. 
• Getting explanations. 
• Debugging code. 
• Getting over writer’s block. 

Limitations 

However, artificial and human intelligence are not the same; these AI tools do not understand anything they produce nor do they understand what the words they produce mean when applied to the real world.  

Open.ai, the creators of ChatGPT, have provided helpful guidance for educators and students – in short: 

• Whilst their output can appear plausible and well written, AI tools frequently get things wrong and can’t be relied upon for factual accuracy. 
• They perform better in subjects which are widely written about, and less well in niche or specialist areas. 
• Unlike a normal internet search, they don’t look up current resources and are currently some months out of date. 
• They cannot currently provide references – they fabricate well formatted but fictitious citations. 
• They can perpetuate stereotypes, biases and Western perspectives. 

More fundamentally, overreliance on these tools will reduce your opportunities to hone your writing, critical thinking, and evaluation skills – key academic and professional skills which you will need as you progress through your studies and beyond. What these tools can provide, however, is an opportunity to build critical analysis and evaluation skills – perhaps by studying and critiquing what they produce, and making judgements about whether what they produce is actually valid and believable.  

AI and academic misconduct 

When you submit work via Moodle or AssessmentUCL you are reminded that: 

Using AI tools to help with such things as idea generation or your planning may be an appropriate use, though your context and the nature of the assessment must be considered. It is not acceptable to use these tools to write your entire essay from start to finish. Also, please bear in mind that words and ideas generated by some AI tools make use of other, human authors' ideas without referencing them, which, as things stand, is controversial in itself and considered by many to be a form a plagiarism. 

Your teachers will be able to provide more specific guidance on what tools, if any, are allowed in the context of your own assignments, but the following applies across all of UCL’s assessments.   

How to acknowledge AI sources in your work 

If your teachers have made clear that you may use AI sources in your assessed work, then you should acknowledge, describe and reference its use: 

You must describe how the information or material was generated (including the prompts you used), what the output was and how the output was changed by you. You should use the following style of wording, depending on the nature of use:  

The following prompts were input into <AI system>: <List prompt(s)> 
The output obtained was: <Paste the output generated by the AI system> 
The output was changed by me in the following ways: <explain the actions taken> 

1. Acknowledge: acknowledge its use

You must acknowledge its use – name the tool and how it was used using the following style. 

• No content generated by AI technologies has been presented as my own work 
• I acknowledge the use of <insert AI system(s) and link> to generate materials for background research and self-study in the drafting of this assessment. 
• I acknowledge the use of <insert AI system(s) and link> to generate materials that were included within my final assessment in modified form. 

2. Describe: you must describe how the information or material was generated

You must describe how the information or material was generated (including the prompts you used), what the output was and how the output was changed by you. You should use the following style of wording, depending on the nature of use:  

• The following prompts were input into <AI system>: <List prompt(s)> 
• The output obtained was: <Paste the output generated by the AI system> 
• The output was changed by me in the following ways: <explain the actions taken> 

3. Reference: final guidance on how to reference AI-generated content

You must describe how the information or material was generated (including the prompts you used), what the output was and how the output was changed by you. You should use the following style of wording, depending on the nature of use:  

• The following prompts were input into <AI system>: <List prompt(s)> 
• The output obtained was: <Paste the output generated by the AI system> 
• The output was changed by me in the following ways: <explain the actions taken> 

Example of how to acknowledge, describe and reference 

Acknowledgement:  

I acknowledge the use of ChatGPT (https://chat.openai.com/) to plan my essay, and generate some initial ideas which I used in background research and self-study in the drafting of this assessment. 

Description of use of AI: 

I used ChatGPT to create a high level structure which I then adapted in my essay, choosing to focus on Bentham’s contribution to philosophy and to utilitarianism, and on the impact on human rights and civil liberties. I used one further ChatGPT prompt to generate some high level ideas about utilitarianism and civil liberties. 

Reference: 

OpenAI, ChatGPT, 15Feb 2023, https://chat.openai.com/APA example: 

Examples of ChatGPT responses to questions: 

Prompt: Write a high level essay plan on 'Was Jeremy Betham a good man?

AI Response: 

I. Introduction  
A. Background information on Jeremy Bentham  
B. Definition of the term "good man"  
C. Thesis statement outlining the arguments to be made in the essay 

II. Bentham's contribution to philosophy  
A. Bentham's utilitarian philosophy  
B. The positive aspects of Bentham's philosophy  
C. Criticisms of Bentham's philosophy 

III. Bentham's advocacy for individual liberty and human rights  
A. Bentham's views on individual liberty and human rights  
B. The impact of Bentham's ideas on civil liberties  
C. Criticisms of Bentham's views on individual liberty and human rights 

IV. Bentham's advocacy for animal welfare  
A. Bentham's views on animal welfare  
B. The impact of Bentham's ideas on the animal rights movement  
C. Criticisms of Bentham's views on animal welfare 

V. Bentham's views on punishment and prisons  
A. Bentham's ideas on prison reform  
B. The impact of Bentham's ideas on the criminal justice system  
C. Criticisms of Bentham's ideas on punishment and prisons 

VI. Conclusion  
A. Restatement of thesis  
B. Summary of the arguments made in the essay  
C. Final assessment of whether Bentham was a good man based on the evidence presented. 

Prompt: Summarise what does utilitarianism mean for civil liberties 

AI Response: 

Utilitarianism is a philosophy that emphasizes the greatest good for the greatest number. In the context of civil liberties, utilitarianism holds that individual liberties should be restricted if it is deemed necessary for the greater good of society. This means that civil liberties may be curtailed in the interest of public safety or welfare, as long as the benefits of doing so outweigh the costs to individual freedoms. Some proponents of utilitarianism argue that this approach can lead to greater social harmony and prosperity, while critics argue that it can lead to abuses of power and violations of individual rights.