AI-enabled software requirements specification for banking chatbot systems
DOI: https://doi.org/10.3846/ntcs.2026.26881Abstract
Software Requirements Specification plays an important role in the success of software development projects by providing clear, structured, and consistent documentation of requirements. However, traditional SRS processes are manual, time-consuming, ambiguous, and inconsistent. This paper proposes an AI-enabled software requirements specification framework using Retrieval-Augmented Generation. The method combines Large Language Models with domain-specific knowledge retrieval to generate structured, coherent, and contextual requirement specifications. The proposed approach integrates document management, semantic retrieval, and generative reasoning to improve requirements quality, reduce ambiguity and enhance traceability. Validation was conducted using a banking chatbot case study. Experimental evaluation showed that the proposed approach achieved 0.75 precision, 1.00 recall, 0.857 F1-score and 0.75 accuracy for Functional Requirement identification on a manually labelled 12-sample evaluation subset. However, the system did not correctly identify Non-Functional Requirements in the current evaluation, indicating the need for a refined FR/NFR classification strategy in future work. The results demonstrate that Retrieval-Augmented Generation provides a practical and scalable solution for modern intelligent requirements engineering systems.
Keywords:
software requirements specification, artificial intelligence, retrieval-augmented generation, large language models, natural language processing, functional requirements, non-functional requirementsHow to Cite
Share
License
Copyright (c) 2026 The Author(s). Published by Vilnius Gediminas Technical University.
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Adamopoulou, E., & Moussiades, L. (2020). Chatbots: History, technology, and applications. Machine Learning with Applications, 2(November), Article 100006. https://doi.org/10.1016/j.mlwa.2020.100006
Ahmad, K., Abdelrazek, M., Arora, C., Bano, M., & Grundy, J. (2023). Requirements practices and gaps when engineering human-centered Artificial Intelligence systems. Applied Soft Computing, 143, Article 110421. https://doi.org/10.1016/j.asoc.2023.110421
Borg, M., & Borg, M. (2024). Requirements engineering and large language models: Insights from a panel. IEEE Software, 41(2), 6–10. https://doi.org/10.1109/MS.2023.3339934
Cheng, H., Husen, J. H., Lu, Y., Racharak, T., Yoshioka, N., Ubayashi, N., & Washizaki, H. (2026). Generative AI for requirements engineering: A systematic literature review. Software – Practice and Experience, 56(2), 141–170. https://doi.org/10.1002/spe.70029
Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazaré, P. E., Lomeli, M., Hosseini, L., & Jégou, H. (2025). the Faiss Library. IEEE Transactions on Big Data, 12(2), 346–361. https://doi.org/10.1109/TBDATA.2025.3618474
Fan, W. Q., Ding, Y. J., Ning, L. B., Wang, S. J., Li, H. Y., Yin, D. W., Chua, T. S., & Li, Q. (2024). A survey on RAG meeting LLMs: Towards retrieval-augmented large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024 (pp. 6491–6501). Association for Computing Machinery. https://doi.org/10.1145/3637528.3671470
Ferrari, A. (2023). Artificial intelligence in engineering and society: Blue skies, black holes, and the job of requirements engineers (keynote). In K. Schneider, F. Dalpiaz, & J. Horkoff (Eds.), 2023 IEEE 31st International Requirements Engineering Conference Workshops, REW (pp. 67–67). IEEE. https://doi.org/10.1109/REW57809.2023.00018
Habiba, U. E., Haug, M., Bogner, J., & Wagner, S. (2024). How mature is requirements engineering for AI-based systems? A systematic mapping study on practices, challenges, and future research directions. Requirements Engineering, 29(4), 567–600. https://doi.org/10.1007/s00766-024-00432-3
Kaur, K., & Kaur, P. (2024). The application of AI techniques in requirements classification: A systematic mapping. Artificial Intelligence Review, 57, Article 57. https://doi.org/10.1007/s10462-023-10667-1
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W. T., Rocktäschel, T., Riedel, S., & Kiela, D. (2020, December). Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020).
Liu, K., Reddivari, S., & Reddivari, K. (2022). Artificial intelligence in software requirements engineering: State-of-the-Art. In 2022 IEEE 23rd International Conference on Information Reuse and Integration for Data Science, IRI (pp. 106–111). IEEE. https://doi.org/10.1109/IRI54793.2022.00034
Maalej, W., Pham, Y. D., & Chazette, L. (2023). Tailoring requirements engineering for responsible AI. Computer, 56(4), 18–27. https://doi.org/10.1109/MC.2023.3243182
Nalchigar, S., Yu, E., & Keshavjee, K. (2021). Modeling machine learning requirements from three perspectives: A case report from the healthcare domain. Requirements Engineering, 26(2), 237–254. https://doi.org/10.1007/s00766-020-00343-z
Niu, C., Wu, Y., Zhu, J., Xu, S., Shum, K., Zhong, R., Song, J., & Zhang, T. (2024). RAGTruth: A hallucination corpus for developing trustworthy retrieval-augmented language models. In L. W. Ku, A. Martins, & V. Srikumar (Eds.), Proceedings of the Annual Meeting of the Association for Computational Linguistics (vol. 1, pp. 10862–10878). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.acl-long.585
Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 3982–3992). Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1410
Siddeshwar, V., Alwidian, S., & Makrehchi, M. (2024). A systematic review of AI-enabled frameworks in requirements elicitation. IEEE Access, 12, 154310–154336. https://doi.org/10.1109/ACCESS.2024.3475293
Sofian, H., Yunus, N. A. M., & Ahmad, R. (2022). Systematic mapping: Artificial intelligence techniques in software engineering. IEEE Access, 10, 51021–51040. https://doi.org/10.1109/ACCESS.2022.3174115
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing and Management, 45(4), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002
Taj, S., Daudpota, S. M., Imran, A. S., & Kastrati, Z. (2025). Aspect-based sentiment analysis for software requirements elicitation using fine-tuned bidirectional encoder representations from transformers and explainable artificial intelligence. Engineering Applications of Artificial Intelligence, 151, Article 110632. https://doi.org/10.1016/j.engappai.2025.110632
Wang, R., Liu, J., Zhang, Q., Fu, C., & hou, Y. (2024). Federated learning for feature-fusion based requirement classification. Cluster Computing, 27(3), 3397–3416. https://doi.org/10.1007/s10586-023-04147-y
Zhang, W., & Zhang, J. (2025). Hallucination mitigation for retrieval-augmented large language models: A review. Mathematics, 13(5), Article 856. https://doi.org/10.3390/math13050856
Zowghi, D., Bano, M., & Borg, M. (2023). What’s missing in requirements engineering for responsible AI? IEEE Software, 40(6), 11–15. https://doi.org/10.1109/MS.2023.3302934
View article in other formats
CrossMark check
Published
Issue
Section
Copyright
Copyright (c) 2026 The Author(s). Published by Vilnius Gediminas Technical University.
License
This work is licensed under a Creative Commons Attribution 4.0 International License.