Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196697,
        author = {Tiruglla Neelima and Srisailam Kakurala and Yamini Kandula and Akash Jatoth and Akshaya Korepu},
        title = {PRISM-NOTE: A Parallel Roadmap-Based Intelligent System for Automated Academic Notes Generation Using Large Language Models},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {4401-4408},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196697},
        abstract = {The rapid growth of digital educational content has increased the need for efficient tools that can transform unstructured academic material into structured study resources. Traditional summarization systems primarily generate short abstracts and fail to produce comprehensive, exam-oriented notes. This paper presents PRISM-NOTE, a Parallel Roadmap-based Intelligent System for automated notes generation using Large Language Models (LLMs). The proposed system accepts syllabus documents, PDFs, or textual inputs and converts them into structured academic notes through a multi-stage pipeline. Initially, text extraction is performed to obtain clean content. A roadmap generation module then identifies key topics and organizes them hierarchically. The core contribution lies in a parallel LLM processing framework, where multiple topics are processed simultaneously using worker threads, significantly reducing generation time. The outputs are aggregated, formatted, and compiled into a structured PDF document, which is stored in cloud storage for future access. Experimental evaluation shows that the system reduces manual effort by approximately 80–85% and achieves a generation speed improvement of 40–55% compared to sequential processing. The proposed approach enables scalable, efficient, and user-friendly academic content generation, addressing limitations of existing summarization tools and providing complete syllabus-oriented notes.},
        keywords = {AI Notes Generation, Large Language Models, Parallel Processing, Roadmap Structuring, Educational AI.},
        month = {April},
        }