Fact-checking and reference hunting
Fact-checking and reference hunting
Description
In this proposal for a learning activity, you can prompt answers from a chatbot that students can use in class. This learning activity is called “Fact-checking and reference hunting” and the general idea is to use a generative AI, prior to the teaching activity, to generate some texts about the subject taught at the lecture. During the class, you will provide the students with these texts and ask them to find references to the claims listed and spot eventual factual mistakes or exaggerations.
Didactic benefits
The didactic benefits of this exercise are manyfold. The learning activity will train the students in how to get inspired by a large language model when writing. The students will engage in a fact-checking process and potentially spot hallucinations from the generative AI, and the students will be trained in finding references. As an educator, you can facilitate a plenary discussion after the process and have a dialogue with the students about the workings of a generative AI platform and the process of fact-checking the generative AI output.
Prompt
In this learning activity, a prompt will not be provided as it depends on the subject you are teaching. When you are prompting the chatbot, for instance, ChatGPT or Bing, instead of simply writing “Write a text about information systems”, you are encouraged to use the tips and tricks about designing and engineering a good prompt. For instance, you should be specific and provide context to your prompt. “Write 200 words about the evolution of the academic field information systems. Please write it in an academic tone”
Bloom's Taxonomy
The learning activity encompass various levels of Bloom’s Taxonomy:
Understanding:
The students need to understand the nuances of the information provided by the generative AI and the importance of cross-referencing it with external sources.
Applying:
The activity requires students to apply their knowledge and skills in fact-checking. They need to apply critical thinking to spot potential errors or exaggerations in the generative AI-generated content.
Analyzing:
Students are engaged in analyzing the generative AI-generated texts, breaking them down into claims and assessing the accuracy of those claims through reference hunting.
Evaluating:
Through fact-checking, students are evaluating the reliability of the information provided by the generative AI. They are also assessing the credibility of the sources they consult for reference.
Principles for digitally supported PBL
If you are not yet familiar with the principles for digitally supported PBL here at Aalborg University, we encourage you to read more about them via the link above.
The case can support the following principle(s):
Variation
Variation as a principle is fulfilled through varying the usage of digital tools to achieve learning. The variation can be achieved at the lecture, course, semester or even programme level. The variation is not a principle limited to teaching but can also be fostered by supporting variation in the project work of the groups.