Educators can use ChatGPT to create practice questions and answer keys for students. With the prompt for grading questions, students can assess their responses against the answer key. Educators can also ask students to create their own sets of questions and answer keys. By exchanging these with classmates, students can challenge themselves with questions created by their peers and verify the accuracy of their answers by using the prompt for grading questions. This method helps students learn by doing and encourages them to work together.
Disclaimer
The AI Prompt Library presents examples to UM students and staff on how to make better use of Generative AI (GenAI) in the educational process. Maastricht University does not recommend the use of any specific GenAI tool. However, you are strongly advised to opt-out of allowing your content to be used to (further) train the GenAI tool of your choice. This can usually be done in Settings.
Given that all information entered into an AI tool will be stored and can be reused by the GenAI tool provider as they deem fit, one should not feed: UM- data, confidential information and trade secrets; personal data and sensitive data relating to you or other people; Copyrighted materials (such as books, academic articles e.t.c.), but also materials for which the UM is the copyright holder, such as educational materials including coursebooks, syllabi, ppt, e.t.c.
Certain GenAI practices in education may not be allowed or encouraged within your faculty’s policy framework and/or rules and regulations. Please check first, any relevant rules on the use of GenAI in education, applicable to you, and defined at activity, course/module, study programme and faculty level.
GenAI can only be employed for high-risk practices under strict conditions set out in the EU AI Act. UM currently refrains from employing GenAI in relation to student assessment, selection and admission procedures, monitoring and detection of prohibited behaviour during exams, pending further thorough investigation of the conditions.
Tips
Tip 1: If awarding partial points is possible, mention it in the grading criteria.
Tip 2: If there is just one answer to be evaluated, it is not necessary to create a loop. The last sentence “Next, ask me for the next student’s answer. Wait for a reply.” can be removed.
The prompt
Copy the example prompt in the box below and paste it into an LLM of your choice.
Note: Modify points 1 – 3 for this prompt to work properly. For points 2 and 3, put your answers in between the special symbols (% and [ ])
Act as a university teacher tasked with grading exam questions. Your job is to evaluate each student’s answer, taking into consideration the following:
1. Exam question: enter a question
2. Answer key: %enter answer key%
3. Grading criteria: [add grading criteria]
Evaluation instruction: Determine whether the student’s answer aligns with the answer key and demonstrates a solid understanding of the relevant concepts. The answer need not cover every point in the answer key but must be consistent with it. Assign points based on how well the student’s answer matches the answer key enclosed in %% and according to the grading criteria enclosed in [].
Output: Provide a breakdown of the points awarded and the reasoning behind awarding the points. Your output must always have the following format:
<Criterion>
<Student’s text that matches the criterion> : <points awarded>
<Reasoning behind awarding the points>
Under <Criterion> insert which criterion you are evaluating. Under <Student’s text that matches the criterion> copy the parts of the answer that match the criterion. Then, after “: “indicate how many points were awarded. Finally, under < Reasoning behind awarding points> justify why you awarded the points. Repeat this for each criterion. At the end, sum up all partial points to show one final score.
First, ask me to provide the student’s answer. Wait for a reply.
Then, evaluate the answer and return the output in the format specified above.
Next, ask me for the next student’s answer. Wait for a reply.
The AI Prompt Library © 2024 by Maastricht University is licensed under CC BY-SA 4.0 .
In case of any questions, please contact the University Library.