How will AI tutoring change

With the recent attention paid to AI because of large language tools such as ChatGPT, my title’s promise to describe change my surprise most educators. Tools for AI tutoring have been deployed and evaluated for some time. I provide a citation in support of this claim at the conclusion of this post. This paper is worth exploring because it offers insights into what has been meant by AI when applied to tutoring and even some insights into human tutoring. For example, I have often quoted the work of Bloom who argued that human tutors probably represented the ideal in teaching and suggested that dedicated intensive tutoring provided a two-standard deviation advantage to those tutored and this advantage represented the best educational interventions could accomplish. I have read the papers in which Bloom made this claim. Kulik and Fletcher offer a different interpretation explaining that Bloom’s data actually involved a combination of tutoring and a mastery approach and the mastery approach may have accounted for at least half of the benefit in this research. That aside, tutoring still offers learners a significant advantage.

Before AI was based on large language models, the AI involved in tutoring was based in a technology-supported system based on a model of what was to be learned, a model of the individual learner, a model of effective instructional strategies, and an interface allowing communication with the system. I had AI generate a description of what the researchers explained these three models involved.

  1. Learner Model: This model represents the student’s knowledge, skills, and learning preferences. It helps the ITS to adapt its teaching strategies to the individual needs of the student.
  2. Teacher Model: This model represents the teaching strategies and pedagogical knowledge used by the ITS to guide the student’s learning process. It helps the ITS to provide appropriate feedback, hints, and explanations.
  3. Content Model: This model represents the subject matter being taught by the ITS. It includes the concepts, relationships, and problem-solving procedures relevant to the domain.

The Kulik review found generally positive benefits for the AI studies, but indicated impact was smaller when the dependent measure was a standardized test rather than local tests, the sample size was small, learners were from the lower grades, the subject was math, MC tests were used as the dependent variable, and the tool studied was Cognitive tutor. For those interested in this type of approach, the review identifies a number of the systems available for use.

My interest in the potential application of the AI tools now available takes a somewhat different approach and suggests that educators and researchers begin with an analysis of the techniques used in successful studying and tutoring and attempt to translate these techniques into tasks that students or educators can apply using AI. I purposefully focus on the research on studying as a general way to think about the cognitive activities of learners following initial experiences which could involve lectures, readings, or any observation of what happens in the world. Simply put, learning requires the processing of external experiences for understanding, retention, and application whether entirely internally and unaided or encouraged by additional external activities (e.g., taking notes, answering questions, discussions with a partner). The natural language capabilities of large language AI allow approximation of these external activities. I have attempted to demonstrate what some of the activities might look like in an earlier post

My prediction is that companies serving the education market will quickly combine the type of AI approaches I have described here (the multi-model approach with the more flexible capabilities of large language models) because of the resources required to do so. You may already see the direction in which this is going be taking note of the efforts of the Kahn Academy (Kahnmigo). 

I do think there are immediate opportunities to take advantage of the tools now available. One distinction that I think educators should consider involves whether activities are applied to the knowledge base used to train the models or applied to designated content. For example, you have ChatGPT ask you multiple choice questions about mitosis or you can ask some AI tools to ask you questions about a pdf or designated content about mitosis. My prediction about commercial ventures will likely be more like this second option as a textbook company would like to focus an AI tutoring approach focused on individual textbooks. There is nothing inherently wrong with either system. I do believe there are more errors when using the more general knowledge base. I also see advantages in controlling the scope of experiences to a designated body of content as a way to control the depth of the experiences. What I mean the discussion of mitosis in a sophomore biology class will be different than in a graduate class because the knowledge base would be different.

I have explored the use of ChatPDF (not ChatGPT) in engaging with the content of a pdf in a previous post. I have been exploring Mem.AI as a way to engage in similar interactions with notes I have taken within this service (you do need the $8 a month version). What I like about this system is that it allows a user to focus the AI prompts on specific material. For example, I could use the service to take class notes on a given day, tag these individual notes or a large page of notes with the date, and then write a prompt to engage with the content identified by this tag. I could also tag notes with a class identifier (PSY101) and then write prompts focused on this tag to review for exams covering more material. I have included several different types of interaction in the material that follows. This material includes my prompts and the AI responses. 

***********************

Me: Using only my knowledge base with tag generative, write a summary of the activities that are classified as generative. Include a list of notes providing this information.

Generative learning activities involve actively engaging with the material to create new knowledge and connections. Some key strategies that promote generative learning include summarization, teaching, self-testing, self-explaining, and notetaking with revision and elaboration. These strategies require learners to select and organize relevant information, elaborate on the material based on personal knowledge, and integrate new information with existing knowledge.

Here are the notes from your knowledge base with the tag “generative”:

  1. Brod’s generative
  2. Summarize my notes on generative learning
  3. Cognitive Activities

These notes provide valuable insights into generative learning strategies and their effectiveness across different age groups, as well as the cognitive processes involved in these activities.

Me: Using only my knowledge base with tag june9, write a summary of the models the author described

Based on your knowledge base with the “june9” tag, here’s a summary of the models described by the author:

In the review by AlShaikh and Hewahi (2021), the authors discuss the development of Intelligent Tutoring Systems (ITS) and their use of multiple models. These models include:

  1. Learner Model: This model represents the student’s knowledge, skills, and learning preferences. It helps the ITS to adapt its teaching strategies to the individual needs of the student.
  2. Teacher Model: This model represents the teaching strategies and pedagogical knowledge used by the ITS to guide the student’s learning process. It helps the ITS to provide appropriate feedback, hints, and explanations.
  3. Content Model: This model represents the subject matter being taught by the ITS. It includes the concepts, relationships, and problem-solving procedures relevant to the domain.

These models work together to create a personalized learning experience for the student. However, the authors note that recent large language models and conversational approaches offer new possibilities for influencing learning without built-in strategies, which could be an important difference in the application of newer general tools.

Me: Using only my knowledge base with tag june9, write a multiple choice questions for me to answer.

Based on your knowledge base with the “june9” tag, here’s a multiple-choice question for you to answer:

In the context of Intelligent Tutoring Systems (ITS) described by AlShaikh and Hewahi (2021), which of the following models is responsible for representing the student’s knowledge, skills, and learning preferences?

A. Learner Model B. Teacher Model C. Content Model D. Language Model

Me: A

That’s correct! The Learner Model in Intelligent Tutoring Systems is responsible for representing the student’s knowledge, skills, and learning preferences. Great job! If you have any more questions or need further clarification, feel free to ask.

References

Kulik, J. A., & Fletcher, J. D. (2016). Effectiveness of intelligent tutoring systems: a meta-analytic review. Review of educational research86(1), 42-78.

Loading