GenAI Academic Prompt Bank

How to use the Prompt Bank

1. Identify what function you would like the Generative AI tool to perform.
2. Select an appropriate prompt from the stems provided below or adapt them to create your own. You may wish to include several of the elements below in a single prompt: for example, a role, a limitation and a requirement.
3. Add as much specific detail to the stem as possible.
4. Generate an output and remember to fact check it for accuracy.
5. Consider whether you would like to build further on this output by selecting a follow-on prompt, or building your own.

Remember: always check with your department to make sure that you are allowed to use AI tools for your academic work.

For more information on using Generative AI for your academic work, please visit the University of Sheffield Generative AI in Assessment pages here.

For example:

	Role	Function	Limitation
Initial prompt	You are an expert [medical practitioner in the field of nursing].	Explore the impact of [cultural care theory] on [patient wellbeing], considering both short-term and long-term effects.	Provide a summary in no more than 500 words.
Follow-on prompt 1		Provide some case studies to illustrate these points.
Follow-on prompt 2		Identify which views may not be as fully represented in this response and why.
Follow-on prompt 3		Where can I find more data on [the potential for stereotyping within cultural care theory]?

---

Build the Prompt Bank

Have you successfully used a prompt to generate a useful output for your academic work? Please share it with us so that we can grow the Prompt Bank. Please note: all submitted prompts will be tested and verified before addition to the Prompt Bank.

Submit your prompts here.

---

Issues to consider when using the Academic Prompt Bank

Accuracy

What is the issue?

GenAI tools are prone to mistakes. Whilst AI tools are trained to produce fluent, coherent outputs, they 'have no understanding of the underlying reality that language describes.' (Lutkevich, 2023). Inaccuracies may include minor inconsistencies, contradictions, or even complete fabrications, including of sources. Watch out for the following:

• Incorrect or false information, which is sometimes referred to as a ‘hallucination’ 
• Inconsistent, or contradictory information
• Fabricated sources that often appear plausible or partially correct

What should I do about it?

• Fact check all information generated by an AI tool using traditional search methods such as StarPlus, Google Scholar, Scopus or Web of Science.
• Use ideas generated by AI tools as a starting point for further reading and research of your own. You will need to make your own evaluation of whether the claims made by an AI tool are accurate.
• Remember never to copy and paste from an AI output or accept an output at face value. You risk incorporating its inaccuracies or inconsistencies into your own work. 

---

Bias

What is the issue?

GenAI is never neutral due to the historical and social biases that are 'baked in' to its training data and the algorithms used to produce outputs. Bias within AI tools can reinforce negative stereotypes, sometimes with serious real-world consequences, for example in the fields of medicine or policing (IBM Data and AI Team, 2023). Be aware of the following in your use of GenAI:

• GenAI outputs may not provide an appropriate level of balance and may privilege certain views over others.
• GenAI outputs may reinforce existing stereotypes including around race, gender, belief or socioeconomic status. 
• GenAI may misinterpret terms used within prompts (for example relating to profession, income or language) resulting in unconscious discrimination against certain groups.

What should I do about it?

• Interpret GenAI outputs with caution being aware of the potential for bias. Be prepared to read around a topic to draw your own objective conclusions. 
• Design prompts thoughtfully to produce outputs that draw on a wide range of views and voices. 
• Use GenAI to explore its own biases, for example by prompting it to explore underrepresented views.

---

Intellectual property

What is the issue?

Inputting information into an AI tool is comparable to putting it in the public domain. In some cases, for example when using data involving personal information or data that is owned by the University, this may breach General Data Protection Regulations or intellectual property laws. You may also wish to consider whether you want to share your own data (for example an essay you have written) in this way. You should be aware of the following:

• You should not share any personal information or otherwise sensitive data with an AI tool without gaining ethical approval to do so.
• You should not share any data that is owned by the University (for example data generated as part of an industrial partnership) with an AI tool.
• You should avoid sharing your own work in its entirety with an AI tool.

What should I do about it?

• If you intend to use GenAI as part of your data analysis, you should seek the necessary permissions and, if appropriate, complete a University ethics application.
• If you would like to use a GenAI tool to gain feedback on your writing, you should consider inputting fragments of your writing only.

---

Simplification

What is the issue?

GenAI is a Large Language Model akin that works in a similar way to predictive text on your phone; it produces an output based on what words and phrases are most likely to follow one another. For this reason, it tends to produce outputs that are generic and bland in character without the idiosyncrasies and originality that set individual writers apart. Watch out for the following: 

• GenAI is no substitute for your own originality and your own unique way of expressing your ideas. Feedback from GenAI may encourage you to adopt a more generic style, which may not improve the authenticity of your writing.
• GenAI will often encourage you to adopt a more definitive and concise style of writing, which may be at odds with the evidence that you are writing about. Using hedging language (for example, 'evidence suggests', 'research indicates', 'may result in') is vital to ensure that you are not overstating your findings.
• GenAI may advise you to avoid using the first person, which may be important in certain circumstances, for example when you are putting forward your own interpretations or writing reflectively.

What should I do about it?

• Use feedback from GenAI tools with caution and only if you feel they are appropriate to your intention as the author.
• Do not make large scale changes to your writing or incorporate substantial chunks of AI-generated text in your work as this may compromise the quality and academic integrity of your writing.

---

Unfair means

What is the issue?

Unfair means refers to methods used by a student that give an unfair advantage over other students in assessments, including helping someone else to gain an unfair advantage. More information is available on the University of Sheffield’s Unfair Means pages.

Even if you make a full disclosure of your use of GenAI, if this is not specifically permitted in your assessment criteria and guidance, or extends beyond what is permitted, there is a risk of this use being considered an unfair advantage, and therefore unfair means.

GenAI responses are not held to the same expectations of accuracy, integrity and ethics as students and staff in academia.  If you use responses from GenAI within your work, you could be using the following types of unfair means either knowingly or without even realising:

• Plagiarism - submitting work or ideas that are not your own, and not attributing the work of others through appropriate referencing.  For example, using a GenAI response as if it is your own work, or using an idea given to you by a response, without knowing or referencing where GenAI found the original idea.

• Buying or commissioning work - submitting work that you have requested a service to produce, and submitting it as if it is your own work.  Even if you have used a free GenAI tool, this is still unfair means if you claim it is your own work.

• Coursework sites - the University does not support the use of sites that share content such as lecture notes, essays, lab reports or exam questions. GenAI may be taking its responses directly from these prohibited sites without you knowing.

• Fabrication - submitting work where some information is made up, such as quotations, results of experiments, or survey findings that are not true.  GenAI does not have the capacity to judge whether its sources are objectively true or accurate and can give a convincing response to a question that it has found no answer for - this is sometimes called AI ‘hallucination’.

• Collusion - submitting work that has been created with the help or input of other people as if it is your own work in an assessment that does not permit group work.  If more than one student has been using GenAI responses within their work and these are similar, this could look like collusion.

What should I do about it?

In assignments where you are sure that you are allowed to use GenAI, you may be asked to provide a full disclosure of how you have done so. This will ensure that your tutor can see how your thinking has intersected with and developed any content that you may have generated. 

You can provide this information by completing an Acknowledge, Describe, Evidence template which you may be asked to submit as an appendix to your assignment.  

1. Acknowledge

Select a statement as appropriate to acknowledge how you used the identified GenAI tool in your work. 

2. Describe

Provide a short summary to describe how you employed the tool and how you adapted or developed its outputs. 

3. Evidence

Provide evidence of how you have used GenAI by providing your prompts and copying and pasting outputs.