A Survey Paper on Edu Bot: Educational Companion to Answer Your Queries Regarding Document Analysis

Aishwarya G; Surabhi Srinivas; Sanjana T S; Shashank G N; Sidharth K Iyer1

1

Publication Date: 2024/12/09

Abstract: The traditional education model often fails to address the varied learning styles and personalized needs of students, leading to disengagement and gaps in knowledge. "Edu_bot," an AI-powered educational tool, is designed to overcome these limitations by leveraging Retrieval-Augmented Generation (RAG) models. Edu_bot offers personalized learning experiences by summarizing content, generating quizzes, and providing real-time support tailored to individual learners' needs. This paper surveys existing solutions in education technology, highlights their limitations, and presents Edu_bot as a solution that integrates dynamic content generation, personalized feedback, and interactive learning, thus enhancing student engagement and learning outcomes.

Keywords: Edu_bot, Personalized learning, Retrieval- Augmented Generation (RAG), Generative AI in education, Adaptive learning,- Educational technology, AI-powered tutoring systems, Real-time feedback, Knowledge retrieval, Interactive learning systems.

DOI: https://doi.org/10.5281/zenodo.14328991

PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT24NOV1720.pdf

REFERENCES

  1. Sahu, N. (2024). The GenAI Revolution: Unleashing the Role of Information Technology in Education. Journal of Educational Technology and Innovation, 15(2), 45-52.
  2. Wei, X., Wang, Y., Chen, L., & Liu, M. (2023). A Survey on Chain-of-Thought Reasoning in Large Language Models. Artificial Intelligence Review, 30(1), 73-91.
  3. Huang, Z., & Huang, F. (2023). Survey of Retrieval-Augmented Text Generation in Large Language Models. Journal of AI and Data Science, 27(3), 188-202.
  4. Soman, S., & Roychowdhury, S. (2024). Observations on Building RAG Systems for Technical Documents. Proceedings of the International Conference on Advanced Computing, 66(4), 233-249.
  5. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2023). Self-RAG: Self-reflective Retrieval-Augmented Generation. Journal of Neural Information Processing, 23(5), 115-132.
  6. Doe, J., & Lee, A. (2023). Rethinking Retrieval-Augmented Language Models for Personalized Document Generation. ACM Transactions on Information Systems, 42(1), Article 16.
  7. Huang, J., Li, M., & Song, R. (2024). Enhancing Clinical NLP with Large Language Models. Journal of Biomedical Informatics, 85, 321-338.
  8. Zhang, Y., & Kim, S. (2024). Fact, Fetch, and Reason: A Unified Assessment of Retrieval-Augmented Generation. Journal of Computational Linguistics, 34(3), 401-418.
  9. Murtaza, T., Rahman, S., & Khan, R. (2024). AI-Based Personalized E-Learning Systems: Issues, Challenges, and Solutions. International Journal of E-Learning and Education Technology, 22(6), 95-111.
  10. Becerra, M., Lopez, G., & Chang, T. (2024). Generative AI-Based Personalized Guidance Tool to Improve the Feedback Process Among MOOC Learners. IEEE Transactions on Learning Technologies, 16(2), 222-234.