Results

Publications

  • Master Thesis in Applied AI Program: Chatting Over Course Material

    “The Role of Retrieval Augmented Generation Systems in Enhancing Academic Chatbots”, by Hélder Monteiro. Supervisor: Hamam Mokayed, LTU. Large Language Models (LLMs) combined with Retrieval-Augmented Systems (RAGs) can enhance learning by improving chatbot responses through external knowledge access. This thesis experiments with various RAG configurations to identify the best fit for high school Physics and undergraduate Mathematics. Two RAG-powered LLMs achieved over 64% accuracy in Physics and 66% in Mathematics.
    Link: https://shorturl.at/IQCUr

  • Master Thesis in applied AI program, LTU
    The aim of the Thesis “Educational Artificial Intelligent Chatbot:Teacher Assistant & Study Buddy”, by Dimitrios Zarris and Stergios Sozos, postgraduate students at the Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering was to investigate LLMs’ ability to provide accurate answers to questions related to specific curriculum and to generate curriculum-related exam tests was performed. To this end, a dataset of 21 questions in Swedish drawn from Biology, Mathematics and Physics textbooks, and answers, both automatically generated by the LLM, and model answers given by experienced teachers, was compiled. The comparison of responses demonstrated the versatility and potential of LLMs in generating diverse, accurate and curriculum-aligned responses.
    Link: https://shorturl.at/GIEqC
  • Presentation at the 5th Panhellenic Conference of Junior Researchers in Science Education and New Technologies in Education, May 10-12, 2024
    Presentation of Thodoris Karafylidis, UCY, titled  “Monsters A.I.: Fears of the educational community about integrating Artificial Intelligence into education”
  • Paper at the 18th INTED2024 conference proceedings, 4-6 March 2024, Valencia, Spain
    AI4EDU joint paper was presented at the 18th INTED2024 Conference. Paper title: AI4EDU: AN INNOVATIVE CONVERSATIONAL AI ASSISTANT FOR TEACHING AND LEARNING
    Link: https://library.iated.org/view/VACALOPOULOU2024AI4
  • Paper at the 16th International Conference on Education and New Learning Technologies EDULEARN, 1-3 July, 2024, Palma, Spain
    AI4EDU joint paper was presented at the 16tg International EDULEARN Conference. Paper title: ENHANCING EDUCATIONAL PARADIGMS WITH LLMs: FROM TEACHER TO STUDY ASSISTANTS IN PERSONALIZED LEARNING
    Link: https://library.iated.org/view/ZARRIS2024ENH