An AI-Enhanced System for Context-Aware Information Retrieval and Summarization in AI-Assisted Learning
| International Journal of Electronics and Communication Engineering |
| © 2025 by SSRG - IJECE Journal |
| Volume 12 Issue 8 |
| Year of Publication : 2025 |
| Authors : Sanket Patil, Zahir Aalam |
10.14445/23488549/IJECE-V12I8P127
How to Cite?
Sanket Patil, Zahir Aalam, "An AI-Enhanced System for Context-Aware Information Retrieval and Summarization in AI-Assisted Learning," SSRG International Journal of Electronics and Communication Engineering, vol. 12, no. 8, pp. 307-315, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I8P127
Abstract:
In AI-assisted learning environments, the capacity to effectively extract and summarize educational content is critical for increasing student comprehension and engagement. This work describes an AI-enhanced approach for context-aware information retrieval and summarization that is specifically designed to extract pertinent text and associated tables and graphics from academic PDFs. The system comprises two phases. The first step employs a hierarchical retrieval technique that uses topic-, heading-, and text-level similarity checks to extract contextually relevant content. In terms of retrieval speed, the framework outperforms existing solutions such as ChatGPT, DeepSeek, and Grok.ai, and it is the only one that supports the extraction of multimodal content, which is vital for technical subjects. In the second phase, the collected content is run through a fine-tuned T5-small language model that is designed for abstractive summarization. The fine-tuned model produces more accurate and cohesive summaries than the base model, while also retaining important visual and structural elements like figures and tables. Comparative evaluations show that the system outperforms in both retrieval performance and summarization quality. The suggested system bridges the gap between text-only and multimodal understanding, providing a scalable and domain-adaptive solution for intelligent content delivery in digital education platforms.
Keywords:
AI-Assisted Learning, Multimodal Summarization, Context-Aware Information Retrieval, Large Language Models, Fine-Tuned Language Models.
References:
[1] Tatwadarshi P. Nagarhalli, Ashwini M. Save, and Narendra M. Shekokar, Fundamental Models in Machine Learning and Deep Learning, 1st ed., Design of Intelligent Applications using Machine Learning and Deep Learning Techniques, Chapman and Hall/CRC Press, pp. 13-36, 2021.
[Google Scholar] [Publisher Link]
[2] What is Information Retrieval?, geeksforgeeks, 2025. [Online]. Available: https://www.geeksforgeeks.org/nlp/what-is-information-retrieval/
[3] S. Prakash, H.R. Shashidhara, and G.T. Raju, “The Role of an Information Retrieval in the Current Era of Vast Computer Science Stream,” International Journal of Soft Computing and Engineering, vol. 3, no. 3, pp. 139-143, 2013.
[Google Scholar] [Publisher Link]
[4] Olalere A. Abass, and Oluremi A. Arowolo, “Information Retrieval Models, Techniques and Applications,” International Research Journal of Advanced Engineering and Science, vol. 2, no. 2, pp. 197-202, 2017.
[Google Scholar] [Publisher Link]
[5] Text Summarization in NLP, geeksforgeeks, 2025. [Online]. Available: https://www.geeksforgeeks.org/nlp/text-summarization-in-nlp/
[6] Alok Pandey, and Aruna Bhat, “A Review on Textual Question Answering with Information Retrieval and Deep Learning Aspect,” 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, pp. 224-229, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Hieu Nguyen Van et al., “Miko Team: Deep Learning Approach for Legal Question Answering in ALQAC 2022,” 2022 14th International Conference on Knowledge and Systems Engineering (KSE), Nha Trang, Vietnam, pp. 1-5, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Suling Zhao et al., “Deep Learning-Based Retrieval Algorithms for Recommendation Systems,” 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA), Shenyang, China, pp. 1155-1160, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Halyna Matsiuk et al., “Application of Information Retrieval Thesaurus for the Improvement of Information Retrieval Technologies in Specific Data Domain,” 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), LVIV, Ukraine, pp. 437-440, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] J.C. Scholtes, “Unsupervised Learning and the Information Retrieval Problem,” 1991 IEEE International Joint Conference on Neural Networks, Singapore, vol. 1, pp. 95-100, 1991.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Irene Benedetto et al., “Leveraging Summarization Techniques in Educational Technology Systems,” 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), Los Alamitos, CA, USA, pp. 415-416, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Denys Aksonov et al., “Question-Answering Systems Development Based on Big Data Analysis,” 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), LVIV, Ukraine, pp. 113-118, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Chenchen Xu, “Research on Information Retrieval Algorithm Based on TextRank,” 2019 34rd Youth Academic Annual Conference of Chinese Association of Automation (YAC), Jinzhou, China, pp. 180-183, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Kishan Kanhaiya et al., “AI Enabled- Information Retrival Engine (AI-IRE) in Legal Services: An Expert-Annotated NLP for Legal Judgements,” 2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India, pp. 206-210, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Hoang-Long Nguyen, Trong-Nhan Trinh-Huynh, and Kim-Hung Le, “Towards a Robust and Scalable Information Retrieval Framework in Big Data Context,” 2022 9th Nafosted Conference on Information and Computer Science (NICS), Ho Chi Minh City, Vietnam, pp. 211-216, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Minnu Helen Joseph, and Sri Devi Ravana, “Generation of High-Quality Relevant Judgments through Document Similarity and Document Pooling for the Evaluation of Information Retrieval Systems,” 2022 14th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), Phnom Penh, Cambodia, pp. 261-265, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Yelisetty Srivarsha, and V.M. Manikandan, “A Novel Content-based Image Retrieval Scheme based on Textual Information,” 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kharagpur, India, pp. 1-4, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Darshana V. Vekariya, and Nivid R. Limbasiya, “A Novel Approach for Semantic Similarity Measurement for High Quality Answer Selection in Question Answering Using Deep Learning Methods,” 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, pp. 518-522, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Tatwadarshi P. Nagarhalli, Vinod Vaze, and N.K. Rana, “A Review of Current Trends in the Development of Chatbot Systems,” 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, pp. 706-710, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, pp. 1-800, 2016.
[Google Scholar] [Publisher Link]
[21] Tatwadarshi P. Nagarhalli, Vinod Vaze, and N.K. Rana, “Impact of Machine Learning in Natural Language Processing: A Review,” 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), Tirunelveli, India, pp. 1529-1534, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Fusheng Wei et al., “Empirical Study of LLM Fine-Tuning for Text Classification in Legal Document Review,” 2023 IEEE International Conference on Big Data (BigData), Sorrento, Italy, pp. 2786-2792, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Colin Raffel et al., T5 Small, Hugging Face. [Online]. Avaliable: https://huggingface.co/google-t5/t5-small
[24] Wei Cui, Zhen Xue, and Khanh-Phuong Thai, “Performance Comparison of an AI-Based Adaptive Learning System in China,” 2018 Chinese Automation Congress (CAC), Xi'an, China, pp. 3170-3175, 2018.
[CrossRef] [Google Scholar] [Publisher Link]