In this video I demonstrate the use of Claude (a generative AI chatbot) to create a series of multiple choice questions from a slideshow.
I describe the prompts I used, and show a few of the mistakes that Claude made, as well as how simple it is to correct them. You can imagine using the same process to create a short series of MCQs after a lecture. And in a more sophisticated version, you could have students upload the lecture slides, and have the AI ask them questions.
I’d love to hear any thoughts or concerns you may have about this process. And, if you try it out, I’d love to hear about your successes or failures.
Comments
2 responses to “Using Claude to generate MCQs from a slideshow”
Update (20-02-2024): I just came across Kıyak, et al. (2024). ChatGPT for generating multiple-choice questions: Evidence on the use of artificial intelligence in automatic item generation for a rational pharmacotherapy exam. European Journal of Clinical Pharmacology, who report that, “…the questions can effectively differentiate between students who perform at high and low levels…”.
Good point, Laura. I didn’t evaluate the quality of the distractors. I’m not even sure if there’d be much value in doing that research, because there’s no consistency / reliability in the outputs. I imagine each case would need to be evaluated independently.
Fantastic clear example, thank you. Really appreciate the way you are thinking out loud.
Am interested to know about the quality of the incorrect answers
Laura