LLM-based Chatbot for Course-based Question Answering

Year : 2023 | Volume : 01 | Issue : 02 | Page : 30 41
    By

    Samyuktha M S,

  • S. Charumathi,

  • Darsana R,

  • S. Lovelyn Rose,

  1. Student, PSG College of Technology, Coimbatore,, Tamil Nadu, India
  2. Student, PSG College of Technology, Coimbatore,, Tamilnadu, India
  3. Student, PSG College of Technology, Coimbatore,, Tamilnadu, India
  4. Associate Professor, PSG College of Technology, Coimbatore,, Tamilnadu, India

Abstract

The “LLM-based Chatbot for Course-Based Question Answering” project addresses the pressing need for tailored and efficient learning tools in education. By using a state-of-the-art Large Language Model (LLM) with a diverse dataset, including textbooks, professor slides, and web scraping data, the chatbot offers accurate and contextually enriched responses to students’ course-related queries. Using recent advances in language modeling, this work presents a Longformer-based Language Model (LLM) for constructing a smart chatbot optimized for course-based question answering (CBQA). The suggested LLM-based chatbot has a user-friendly interface where students can submit questions on various subjects, topics, or concepts presented in their courses. The chatbot uses natural language understanding techniques to extract relevant information and generate responses to these requests. The LLM-based chatbot’s key feature is its capacity to answer a wide range of question kinds, including factual, conceptual, and problem-solving queries. Through fine-tuning individual course materials, the chatbot adapts to the unique vocabulary and content of different disciplines, ensuring accurate and contextually relevant responses. It also features a function for extracting chapter summaries and generating concise study notes, facilitating efficient revision. The project’s outcomes include providing students with a robust tool for course clarification, enabling them to practice with relevant materials, and streamlining the revision process, ultimately enhancing the learning experience within the specified college.

Keywords: LLM based Chatbot, Large Language Model (LLM), Natural Language Processing (NLP), Question Answering (QA) Systems, processing, Chapter summaries, Efficient revision, Course clarification, Academic enhancement

[This article belongs to International Journal of Electronics Automation ]

How to cite this article:
Samyuktha M S, S. Charumathi, Darsana R, S. Lovelyn Rose. LLM-based Chatbot for Course-based Question Answering. International Journal of Electronics Automation. 2024; 01(02):30-41.
How to cite this URL:
Samyuktha M S, S. Charumathi, Darsana R, S. Lovelyn Rose. LLM-based Chatbot for Course-based Question Answering. International Journal of Electronics Automation. 2024; 01(02):30-41. Available from: https://journals.stmjournals.com/ijea/article=2024/view=145756


Browse Figures

References

  1. Gao Y, Baptista‐Hon DT, Zhang K. The inevitable transformation of medicine and research by large language models: the possibilities and pitfalls. MEDCOMM-Future Medicine. 2023 Jun 1;2(2).
  2. Peng B, Galley M, He P, Cheng H, Xie Y, Hu Y, Huang Q, Liden L, Yu Z, Chen W, Gao J. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813. 2023 Feb 24.
  3. Zhang P, Jaipersaud B, Ba J, Petersen A, Zhang L, Zhang MR. Classifying Course Discussion Board Questions using LLMs. In Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 2 2023 Jun 29 (pp. 658-658).
  4. Ling C, Zhao X, Lu J, Deng C, Zheng C, Wang J, Chowdhury T, Li Y, Cui H, Zhao T. Beyond one-model-fits-all: A survey of domain specialization for large language models. arXiv preprint arXiv:2305.18703. 2023;1.
  5. Yager KG. Domain-specific chatbots for science using embeddings. Digital Discovery. 2023;2(6):1850-61.
  6. Chen YH, Senk SL, Thompson DR, Voogt K. Examining psychometric properties and level classification of the van Hiele Geometry Test Using CTT and CDM Frameworks. Journal of Educational Measurement. 2019 Dec;56(4):733-56.
  7. Tripathi KP. A study of interactivity in human-computer interaction. International Journal of Computer Applications. 2011 Feb 28;16(6):1-3.
  8. Dehelean T, Nafornita C, Isar A. Estimate’s Statistics in the Performance Evaluation of Extended Object Tracker. In2019 International Symposium on Signals, Circuits and Systems (ISSCS) 2019 Jul 11 (pp. 1-4). IEEE.
  9. Dev A, Parmanand B. A Novel Feature Extraction Technique for Speaker Identification. International Journal of Computer Applications. 2011 Feb;16(6):0975-8887.
  10. Jeon J, Lee S. Large language models in education: A focus on the complementary relationship between human teachers and ChatGPT. Education and Information Technologies. 2023 Dec;28(12):15873-92.
Regular Issue Subscription Original Research
Volume 01
Issue 02
Received 15/03/2024
Accepted 30/03/2024
Published 10/04/2024
728

Login


My IP

PlumX Metrics