NotebookLM’s Mind Map: A Hidden Gem

Understanding NotebookLM's Core Features

NotebookLM is one of the most interesting and potentially useful tools on the generative AI (GAI) landscape. It’s simply awesome. Basically, NotebookLM allows you to upload documents, audio files, or provide links to videos and websites, then use interact with the information in those resources. It’s a form of retrieval augmented generation (RAG), which essentially means that it will use the sources you provide when crafting responses to prompts. Rather than just relying on its original training data, NotebookLM uses the sources you provide to develop its responses.

I use NotebookLM extensively in my doctoral seminars. It allows me to get concise yet comprehensive summaries of each week’s readings. More importantly, it helps me identify areas that might be confusing to my students. Recently, I’ve been using NotebookLM to help me organize materials related to my research. Although it is no substitute for the work of digging into a topic, it can help streamline the process. I’ll write more about this in the future. Today, I want to focus on an underutilized feature, NotebookLM’s Mind Map.

At first, I was pretty skeptical of Mind Map. After all, the point of creating a mind map (sometimes called a cognitive map) is to organize your thinking about a concept or topic. If AI creates a mind map for me, what’s the point? But, after playing around with Mind Map a bit, I’ve changed my mind. Seeing how AI organizes a topic is much more helpful than I thought it would be.

Mind Map in Action: An AI Bias Example

Let’s look at an example. I was working on a short paper on a specific aspect of AI bias. The editor of the volume to which the paper was being submitted asked us (my co-author and me) to include a short section on AI bias in general. I did some literature searches, identified some key articles and uploaded them into NotebookLM. (NotebookLM Plus, the paid version, can accept up to 300 sources, which is pretty amazing.) Then, I asked NotebookLM to create a Mind Map by clicking on the Mind Map button.

NotebookLM created the Mind Map below:

Let’s take a look at this. First, it’s a pretty reasonable way to organize my section on AI bias. I even like the order in which the sub-concepts are presented. It seems like a logical flow to me. Clicking on the > after each concept expands that concept, as shown below:

That’s quite a list. Discussing all of these would probably be too long for a short section, so I focused on the most common sources. Also, there’s some overlap, for example with data bias and training data bias. In fact, several of these could be aggregated to create a smaller set. This is a critical point. I didn’t take NotebookLM’s Mind Map as the last word. It is simply a useful starting point. There was still quite a bit of thinking for me to do.

One of the best features of Mind Map is not at all obvious; in fact, it’s kind of hidden. Double-clicking on one of the concepts in green brings up a chat window that dives into that concept, using the sources you provided.

Check this out. I wasn’t familiar with deployment bias, so I double-clicked on it, which brought up this chat window:

Notice the footnotes. Clicking on one of the footnotes opens a Sources window that takes you to the specific location within the source that was the basis for NotebookLM’s response. To dig into deployment bias more, all I need to do is go back to the original sources.

I didn’t ask NotebookLM to write a single word of the article, but it was still a huge help on this particular section. Although it’s hard to say precisely, my best guess is that using NotebookLM cut the time required to write this section by at least 50%. To me, that’s huge.

Beyond the Basics: Combining Deep Research and Mind Map

We can make this even more interesting if we use a deep research report as a source. Although AI-generated deep research reports are no substitute for “real” research, they are excellent ways to get up to get up to speed quickly in an area. Suppose you’re asked to give a talk on how AI is affecting critical thinking. You could use ChatGPT, Gemini, or Perplexity to create a deep research report, like this one, which was produced with Gemini. (ChatGPT’s tend to be much more in-depth.)

Here’s how I would use deep research and Mind Map to help. First, I’d upload Gemini’s deep research report as a source in NotebookLM, then ask NotebookLM to produce a Mind Map. Here’s part of the result when I actually did this:

My involvement in this took about 3 minutes, although I had to wait 10 minutes or so for Gemini to create the deep research report initially. So in a very short period of time, I had a solid structure for and a big head start on putting together the talk. Yes, I still need to verify all of this and think through how I would make the content mine, but I’ve saved quite a bit of time. Also, I might have identified some aspects of the topic I might not have considered on my own.

NotebookLM's Mind Map feature represents a powerful tool for anyone who needs to quickly understand and organize complex information. Whether you're writing an article, preparing a talk, or just trying to wrap your head around a new topic, Mind Map can help streamline the process. More importantly, it can help identify connections and concepts you might have missed on your own. While it's no substitute for careful thought and analysis, Mind Map can significantly reduce the time required to get from initial research to final product. That's not just efficient, it's transformative.

---

Want to continue this conversation? I'd love to hear your thoughts on how you're using AI to develop critical thinking skills in your courses. Drop me a line at Craig@AIGoesToCollege.com. Be sure to check out the AI Goes to College podcast, which I co-host with Dr. Robert E. Crossler. It's available at https://www.aigoestocollege.com/follow.

Looking for practical guidance on AI in higher education? I offer engaging workshops and talks—both remotely and in person—on using AI to enhance learning while preserving academic integrity. Email me to discuss bringing these insights to your institution, or feel free to share my contact information with your professional development team.