After taking a little time off, Im ready to jump back in to focus on developing active learning activities for students with the help of an LLM (Large Language Model).

Background

First, let’s look at active learning versus passive learning. Active learning invites students to actively engage with the instructional material rather than passive receivers of knowledge. Active learning allows students to discuss, work in teams, take on roles, or may be as simple as reflecting on their learning. Passive learning tends to be what is seen as traditional, watching/listening to lectures or reading articles or textbook chapters. While there are needs for passive forms of learning in courses, students that participate tend to do better in courses that use active learning (Freeman et al., 2014).

One thing to consider when incorporating active learning in a course is that students may experience a disconnect between their perceived and actual learning, feeling as though they have learned less than they actually have. This feeling is due to an increase in cognitive load on learners, as the structure feels “disfluent” (as opposed to the fluent feeling of lectures being organized and smooth) and forces learners to struggle with the material. While the struggle can feel like a lack of learning, it actually signals deeper cognitive processing (Deslauriers et al., 2019)

Using an LLM to help create active learning opportunities can help students to grapple with the material in a deeper way and can save you time in creating these types of activities. We have illustrated ways that you can use LLMs in your courses to create active learning in some of our previous entries (Dungeons & Dragons and Higher Ed and Your Lecture Needs More Stage Presence). This is where an LLM can be particularly useful, not to replace your teaching expertise but to generate new ideas and lighten the creative load.

How an LLM Can Support Active Learning Design

When using an LLM to help develop active learning opportunities, or really anything, it is important to remember that it is a tool and still requires the expertise of the instructor who knows their content and students best. This tool can help to accelerate and expand idea generation, here are some potential ways you might use the LLM to generate a variety of active learning activities:

• Generating Case Studies – input a topic or concept and have the LLM produce realistic scenarios for students to analyze, debate, or solve
• Creating Practice Problems – ask for questions with varying levels of difficulty, or even “worked examples with errors” for students to analyze and correct
• Designing Role-Playing Activities – prompt the model to generate dialogue or character profiles students can take on in a simulation
• Writing Reflection Prompts – ask for questions that encourage students to connect course concepts to their experiences or professional goals
• Developing Peer Discussion Starters – have the model draft open-ended prompts along with example “starter responses” to model rich participation

One thing to keep in mind when using prompts like this is that you are key to making these work. LLMs are not infallible, they can hallucinate, show bias, or be inaccurate and need to be checked – for more on this, check out the Hi-Ho Framework post.

Examples in Action

Imagine you are teaching a course on data ethics. You could prompt an LLM to generate a case study where a company’s use of customer data leads to ethical dilemmas. Students could be assigned to different roles (e.g. CEO, data scientist, policy maker, consumer advocate) and asked to debate potential solutions.

The heavy lifting for this activity will be done by the LLM, but as an instructor you control the framing, relevance, and assessment.

Moving Forward

Like any use of an LLM when developing a course, the goal is not to replace the instructor or the course designer, but to work as a partner and to take on some of the time consuming tasks. To bring in active learning into your course, you don’t need to start with a huge project, you can start with small steps, like drafting discussion questions, reflection prompts, or a simple case study. As you get more comfortable and over time you can expand on what you have done.

Citations

Deslauriers, L., Mcarty, L. S., Miller, K., and Kestin, G. (2019). Measuring actual learning versus feeling of learning in response to being actively engaged in the classroom. Proceedings of the National Academy of Sciences, 116(39), 19251-19257. https://doi.org/10.1073/pnas.1821936116

Freeman, S., Eddy, S.L., McDonough, M., Smith, M.K., Okoroafor, N., Jordt, H., and Wenderoth, M.P. (2014). Active learning increases student performance in science, engineering, and mathematics. Proceedings of the National Academy of Sciences, 111(23), 8410–8415. https://doi.org/10.1073/pnas.1319030111.

Note the featured image was created using ChatGPT.