Successful Learning with LLM Tutors: Patterns of Effective Interaction
Examining human-machine interaction with Large Language Model (LLM)-based tutors to identify patterns indicative of successful human learning.
Duration: January 2026 – December 2026
Status: Ongoing
Educational Level: Lower Secondary Level, Upper Secondary Level – Vocational Education, Upper Secondary Level – Grammar School Education, Tertiary Level
Topic: Artificial Intelligence AI, Data Science for Education, Digital Skills & Literacy, Digital Tools
Keywords: LLM Tutors, Human-Machine Interaction, Effective Learning, Individual Differences
Initial Situation
Recent advances in generative AI have enabled LLM-based chatbots to enhance personalized learning. One promising application is their use as Socratic tutors that stimulate active learning and critical thinking by posing thought-provoking questions rather than providing direct answers. However, the impact of LLMs on learning depends on how they are used. Active engagement and critical thinking, such as identifying and questioning plausible but incorrect information, can promote deep learning. In contrast, passive use may lead to cognitive offloading: tasks are completed correctly, but with little understanding and minimal long-term learning. This underscores the importance of equipping learners with the skills needed to use LLMs in ways that genuinely support learning.
Objectives
The aim of this project is to identify features in interactions between students and an LLM-based tutor that are linked to effective learning, while also examining how individual characteristics like prior knowledge, cognitive ability, motivation, and technology acceptance influence interaction quality. Since analyzing these interactions is time-intensive and partly requires human expertise, the project also explores how this process can be automated. Finally, the findings will inform the development of training materials for students and teachers to improve LLM-based tutoring.
Method
The project builds on a learning sequence with an LLM-based tutor developed in a previous BeLEARN project. Student–tutor interactions from a 2025 blended learning course will be analyzed to identify features linked to learning success. Methods will include natural language processing, machine learning, language models, and expert evaluations. To investigate the role of individual learner characteristics, students will complete a cognitive potential assessment, and we will assess their prior knowledge, motivation and technology acceptance. Based on each measure, they will be grouped into low, medium, and high levels, and differences in key interaction features will be analyzed across these groups. The project will be tested across higher education, secondary schools, and workplace learning.
Planned Translation
Following the implementations of the learning sequence and the training for teachers in various educational contexts within the project, the entire learning sequence will be released as an open-source solution on GitHub, ensuring broad public accessibility. The fully open-source workflow is designed with transferability in mind: educators across disciplines and educational levels will be able to adapt the materials to their specific teaching contexts, promoting efficient and reflective use of LLMs in learning. From both a scientific and societal perspective, it is crucial to understand how to teach learners to use LLMs appropriately, as the rapid development of these technologies is driving significant societal change. At the same time, promoting equity in education requires that we account for the diverse needs of learners to prevent existing disparities between learners from growing even further. This project aims to identify the key characteristics of student-LLM tutor interactions that are associated with high interaction quality and to incorporate the relevant findings into the training of students and teachers. The usefulness of this approach will be evaluated by both students and teachers across different educational contexts.
