Citation :

Amit Virmani, Alok Kumar, Vineeta Singh, "An Autoregressive Secant Optimization-Based Dual-View Retrieval-Augmented LLM Framework for Question Answering," International Journal of Computer Trends and Technology (IJCTT), vol. 74, no. 5, pp. 20-35, 2026. Crossref, https://doi.org/10.14445/22312803/IJCTT-V74I5P104

Abstract

A Question Answering System (QAS) is an Artificial Intelligence (AI) system that automatically understands a user’s question in natural language and provides a precise list of documents that are retrieved. These systems face several difficulties, like understanding context, handling ambiguity in language, and generalization issues. Therefore, a new model, named Autoregressive Secant Optimization-based Retrieval-Augmented Generation Dual View Network (AuRSO-RAGNet), is established for question answering. The proposed model is based on the Taylor-aware Query-RAG Dual View Network with Large Language Model (TQ-RAGNetLLM). The TQ-RAGNet is designed by modifying the Passage Question Answering- Retrieval Augmented Generation (PQA-RAG) approach’s learning rule employing Taylor-Aware Neighbor Mean Square Loss (TANMSL). Answer generation is performed by processing the input passage and questions using PQA-RAG, which comprises two main components: a Question-Dual View Modeling (Q-DVM) and a Question-RAG (Q-RAG) Layer. The overall model is trained using the AuRSO for increasing the performance, where the AuRSO is designed by fusing a Conditional Autoregressive Value-at-Risk (CAViaR) as well as a Secant Optimization Algorithm (SOA). Moreover, experimental outcomes demonstrate that the AuRSO-RAGNet attained a superior recall of 98.248%, precision of 97.840%, and an F1-score of 98.043%.

Keywords

Deep Learning, Question Answering System, Large Language Modelling, Retrieval-Augmented Generation, Natural Language Processing.

References

[1] Priti Gumaste et al., “Automated Question Generator System using NLP Libraries,” International Research Journal of Engineering and Technology, vol. 7, no. 6, pp. 4568-4572, 2020.
[Google Scholar] [Publisher Link]

[2] Eman Mohamed Nabil Alkholy, Mohamed Hassan Haggag, and Amal Aboutabl, “Question Answering Systems: Analysis and Survey,” International Journal of Computer Science & Engineering Survey, vol. 9, no. 6, pp. 1-13, 2018.
[Google Scholar] [Publisher Link]

[3] Rohit Arora et al., “Comparative Question Answering System Based on Natural Language Processing and Machine Learning,” International Conference on Artificial Intelligence and Smart Systems, pp. 373-378, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Kushwanth Sai Lalam et al., “Question Answering System Using NLP,” International Research Journal of Engineering and Technology, pp. 1658-1661, 2021.
[Publisher Link]

[5] Y. Sharma and S. Gupta, “Deep Learning Approaches for Question Answering System,” Procedia Computer Science, vol. 132, pp. 785-794, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Vaishali Fulma, K.P. Moholkar, and S.H. Patil, “The Implementation of Question Answer System using Deep Learning,”  Turkish Journal of Computer and Mathematics Education, vol. 12, no. 15, pp. 176-182, 2021.
[Google Scholar] [Publisher Link]

[7] Arefeh Kazemi et al., “FarsNewsQA: A Deep Learning-Based Question Answering System For The Persian News Articles,” Information Retrieval Journal, vol. 26, no. 1, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Yan Zhao et al., “LB-KBQA: Large-Language-Model and BERT based Knowledge-Based Question and Answering System,” IEEE 22^nd International Conference on Industrial Informatics, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Juan Sequeda, Dean Allemang, and Bryon Jacob, “Knowledge Graphs as a Source of Trust for LLM-Powered Enterprise Question Answering,” Journal of Web Semantics, vol. 85, pp. 1-6, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Jinlu Zhang et al., “HSM-QA: Question Answering System Based on Hierarchical Semantic Matching,” IEEE Access, vol. 11, pp. 77826-77839, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Hainan Wang, “Automatic Question-Answering Modeling in English by Integrating TF-IDF and Segmentation Algorithms,” Systems and Soft Computing, vol. 6, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Jafar A. Alzubi et al., “COBERT: COVID-19 Question Answering System using BERT,” Arabian Journal for Science and Engineering, vol. 48, no. 8, pp. 11003-11013, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[13] B.P. Swathi, M. Geetha, and M.V. Suhas, “Enhancing Query Understanding in Educational Question Answering Systems Through Neural Models,” IEEE Access, vol. 14, pp. 19920-19933, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Qidong Liu et al., “LLM-ESR: Large Language Models Enhancement for Long-Tailed Sequential Recommendation,” Advances in Neural Information Processing Systems, vol. 37, pp. 26701-26727, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Mohammed Q. Ibrahim et al., “Secant Optimization Algorithm for Efficient Global Optimization,” Scientific Reports, pp. 1-50, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Robert F. Engle, and Simone Manganelli, “CAViaR: Conditional Autoregressive Value at Risk by Regression Quantiles,” Journal of Business & Economic Statistics, vol. 22, no. 4, pp. 367-381, 2004.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Wei Yuan, and Wenbo Xu, “Neighborloss: A Loss Function Considering Spatial Correlation for Semantic Segmentation of Remote Sensing Image,” IEEE Access, vol. 9, pp. 75641-75649, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Ming-Chun Lee, and Wei-Ho Chung, “Mean Square Error (MSE) Based Hybrid Analog and Digital Combining for Systems with Large Receive Antenna Arrays,” IEEE 18^th International Workshop on Signal Processing Advances in Wireless Communications, pp. 1-6, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[19] R. Barrio et al., “Breaking the Limits: The Taylor Series Method,” Applied Mathematics and Computation, vol. 217, no. 20, pp. 7940-7954, 2011.
[CrossRef] [Google Scholar] [Publisher Link]

[20] XQuAD Dataset 2026. [Online]. Available: https://github.com/google-deepmind/xquad

[21] MultiLingual Question Answering (MLQA) Dataset, 2026. [Online]. Available: https://github.com/google-deepmind/xquad

[22] Mengqi Li, and Rufu Qin, “DualGraphRAG: A Dual-View Graph-Enhanced Retrieval-Augmented Generation Framework for Reliable and Efficient Question Answering,” Applied Sciences, vol. 16, no. 5, pp. 1-2026.
        [CrossRef] [Google Scholar] [Publisher Link]