This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Niket Singh,
Raj Singh,
- Research Scholar, MCA Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharashtra, India
- Research Scholar, MCA Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharashtra, India
Abstract
This paper presents a detailed framework for developing personalized chatbots that utilize large language models (LLMs) to process and extract information from extensive documents while effectively responding to user inquiries. The proposed system is designed to mitigate information overload by employing advanced natural language processing techniques, leveraging technologies such as OpenAI, LangChain, and Streamlit. By integrating these tools, the framework enhances knowledge retrieval, simplifies document comprehension, and improves overall productivity. The study delves into the architecture, implementation, and practical applications of the framework, demonstrating its ability to streamline access to critical information. Furthermore, it explores how developers and researchers can leverage this system to create end-to-end solutions for document summarization and automated question-answering. Through a structured and step-by-step approach, this research provides valuable insights into constructing intelligent chatbot systems capable of efficiently managing vast amounts of textual data. Ultimately, the proposed framework contributes to the advancement of AI-driven knowledge management and human- computer interaction.
Keywords: Large Language Models, Langchain, ChatBots, Streamlit, OpenAI
Niket Singh, Raj Singh. Leveraging Large Language Models for Personalized Document Summarization and Question Answering: An Architecture for Stoner-Friendly Chatbots. Journal of Artificial Intelligence Research & Advances. 2025; 12(03):-.
Niket Singh, Raj Singh. Leveraging Large Language Models for Personalized Document Summarization and Question Answering: An Architecture for Stoner-Friendly Chatbots. Journal of Artificial Intelligence Research & Advances. 2025; 12(03):-. Available from: https://journals.stmjournals.com/joaira/article=2025/view=0
References
- Balage Filho, Pedro Paulo, TA Salgueiro Pardo, and M. das Gracas Volpe Nunes. “Summarizing scientific texts: Experiments with extractive summarizers. In Seventh International Conference on Intelligent Systems Design and Applications (ISDA 2007), pp. 520-524. IEEE, 2007.
- Bang, Junseong, Byung-Tak Lee, and Pangun Park. “Examination of Ethical Principles for LLM-Based Recommendations in Conversational AI. In 2023, International Conference on Platform Technology and Service (PlatCon), pp. 109-113. IEEE, 2023.
- Prasad, Rajesh S., U. V. Kulkarni, and Jayashree, R. Prasad. “Machine learning in evolving connectionist text summarizer. In 2009, 3rd International Conference on Anti-Counterfeiting, Security, and Identification in Communication, pp. 539-543. IEEE, 2009.
- Developing Ilm apps fast.” In International Conference on Applied Engineering and Natural Sciences, vol. 1, no. 1, pp. 1050- 1056. 2023.
- Monks, Thomas, and Alison Harper. “Improving the usability of open health service delivery simulation models using Python and web apps. NIHR Open Research 3 (2023).
- Pokhrel, Sangita, and Shiv Raj Banjade. AI Content Generation Technology based on Open AI Language Model.” Journal of Artificial Intelligence and Capsule Networks 5, no. 4 (2023): 534-548.
- S, Adith Sreeram A, and Pappuri Jithendra Sai. “An Effective Query System Using LLMS and Langchain.” International Journal of Engineering Research & Technology,July 4, 12(6), 2023. 367 -369
- Liu, Yixin, Alexander R. Fabbri, Pengfei Liu, Dragomir Radev, and Arman Cohan. “On learning to summarize with large language models as references.” arXiv preprint arXiv:2305.14239 (2023).
- Gaur, Vedant, and Nikunj Saunshi. & Symbolic math reasoning with language models. In 2022 IEEE MIT Undergraduate Research Technology Conference (URTC), pp. 1-5. IEEE, 2022.
- Mansurova, Aigerim, Aliya Nugumanova, and Zhansaya Makhambetova. Development of a question-answering chatbot for blockchain domain.” Scientific Journal of Astana IT University (2023): 27- 40.
- Shibi, Krithick, R. Kingsy Grace, and M. Sri Geetha. “Abstractive Summarizer using Bi-LSTM.” In 2022 International Conference on Edge Computing and Applications (ICECAA), pp. 1605-1609. IEEE, 2022
- Nalini, N., Agrim Narayan, Akshay Mambakkam Sridharan, and Arkon Pradhan. “Automated Text Summarizer Using Google Pegasus.” In 2023, International Conference on Smart Systems for Applications in Electrical Sciences (ICSSES), pp. 1– 4. IEEE, 2023.
- Patil, Dinesh D., Dhanraj R. Dhotre, Gopal S. Gawande, Dipali S. Mate, Mayura V. Shelke, and Tejaswini S. Bhoye. Transformative trends in generative ai: Harnessing large language models for natural language understanding and generation.” International Journal of Intelligent Systems and Applications in Engineering 12, no. 4s (2024): 309- 319.
- Topsakal, Oguzhan, and Tahir Cetin Akinci. Creating large language model applications utilizing langchain:

Journal of Artificial Intelligence Research & Advances
| Volume | 12 |
| 03 | |
| Received | 06/03/2025 |
| Accepted | 06/04/2025 |
| Published | 08/07/2025 |
| Publication Time | 124 Days |
[first_name] [last_name]