Close
Guidance on how you might engage with this in your assessments effectively and ethically.
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.
It is important you do not use AI tools to generate an essay and submit it as if it was your own work. In this briefing, we explain how AI might be used and how to acknowledge its use.
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.
- 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 WISEflow you are reminded that:
'Academic Misconduct is strictly prohibited, including the use of essay mills, homework help sites, plagiarism, collusion, falsification, impersonation or any other action which might give me an unfair advantage'.
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.
An unfair advantage is:
- When you hide something and aren't transparent about your approach.
- When you take something directly from someone (or something) else and don't reference or acknowledge.
- When you don't use something in an appropriate way.
- When you don't follow the assessment guidance.
If teaching staff suspect that you are trying to pass off AI-generated output as your own work then the regulations in the Academic Manual (9.2.1 g, h and m) apply. You would be likely to be invited to an investigatory viva to probe the authorship of your work
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. The Library Skills pages share guidance on how to acknowledge and reference AI in your work.