@inproceedings{han-choi-2025-beyond,
    title = "Beyond Linear Digital Reading: An {LLM}-Powered Concept Mapping Approach for Reducing Cognitive Load",
    author = "Han, Junzhi  and
      Choi, Jinho D.",
    editor = {Kochmar, Ekaterina  and
      Alhafni, Bashar  and
      Bexte, Marie  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Tack, Ana{\"i}s  and
      Yaneva, Victoria  and
      Yuan, Zheng},
    booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.bea-1.58/",
    pages = "805--817",
    ISBN = "979-8-89176-270-1",
    abstract = "This paper presents an LLM-powered approach for generating concept maps to enhance digital reading comprehension in higher education. While particularly focused on supporting neurodivergent students with their distinct information processing patterns, this approach benefits all learners facing the cognitive challenges of digital text. We use GPT-4o-mini to extract concepts and relationships from educational texts across ten diverse disciplines using open-domain prompts without predefined categories or relation types, enabling discipline-agnostic extraction. Section-level processing achieved higher precision (83.62{\%}) in concept extraction, while paragraph-level processing demonstrated superior recall (74.51{\%}) in identifying educationally relevant concepts. We implemented an interactive web-based visualization tool https://simplified-cognitext.streamlit.app that transforms extracted concepts into navigable concept maps. User evaluation (n=14) showed that participants experienced a 31.5{\%} reduction in perceived cognitive load when using concept maps, despite spending more time with the visualization (22.6{\%} increase). They also completed comprehension assessments more efficiently (14.1{\%} faster) with comparable accuracy. This work demonstrates that LLM-based concept mapping can significantly reduce cognitive demands while supporting non-linear exploration."
}