AI-Assisted Requirements Engineering Using Multimodal Language Models

  • Authors

    • Karthik Raman Software Architect, Tata Consultancy Services, India. Author

    DOI:

    https://doi.org/10.67228/30715628/IJMIET-2019PI8W8J

    Published 01-03-2019

  • Multimodal Language Models, Requirements Engineering, AI-Assisted Software Engineering, Requirements Elicitation, Requirements Classification, Requirements Validation, Traceability, Natural Language Processing, Human-AI Collaboration, Software Requirements Specification (SRS)

    Issue

    Vol. 2 No. 1 (2019)

    Section

    Articles

  • Abstract

    The rapid advancement of multimodal large language models (MLLMs) has introduced new opportunities to enhance Requirements Engineering (RE) processes through automated understanding of textual, visual, and conversational artifacts. This paper investigates how MLLMs can support key RE activities—including requirements elicitation, classification, validation, conflict detection, prioritization, and documentation—by leveraging their ability to process heterogeneous project inputs such as stakeholder conversation transcripts, UI sketches, system diagrams, and domain documents. We present a conceptual framework for integrating MLLMs into existing RE workflows, highlighting their potential to reduce ambiguity, accelerate requirement refinement, and improve traceability. Through experimental evaluation and case studies, we demonstrate that MLLM-powered RE assistance can significantly increase requirement accuracy and analyst productivity. Finally, we discuss risks such as hallucination, data privacy, and model bias, and propose mitigation strategies and future research directions for reliable adoption of AI-assisted RE systems.

  • References

    [1] Dalpiaz, F., Ferrari, A., Franch, X., & Palomares, C. (2018). Natural Language Processing for Requirements Engineering: The Best Is Yet to Come. IEEE Software, 35(5), 115–119.

    [2] Ferrari, A., Dell'Orletta, F., Esuli, A., Gervasi, V., & Gnesi, S. (2017). Natural Language Requirements Processing: A 4D Vision. IEEE Software, 34(6), 28–35.

    [3] Ahmed, H., Hussain, A., & Baharom, F. (2018). The Role of Natural Language Processing in Requirement Engineering. International Journal of Engineering & Technology, 7(4), 168–171.

    [4] Lucassen, G., Robeer, M., Dalpiaz, F., van der Werf, J. M. E. M., & Brinkkemper, S. (2017). Extracting Conceptual Models from User Stories with Visual Narrator. Requirements Engineering, 22(3), 339–358.

    [5] Dawood, O. S., & Sahraoui, A. E. K. (2017). From Requirements Engineering to UML Using Natural Language Processing – Survey Study. European Journal of Engineering and Technology Research, 2(1), 1–8.

    [6] Garigliano, R., Perini, D., & Mich, L. (2018). Which Semantics for Requirements Engineering: From Shallow to Deep. Proceedings of the 1st Workshop on Natural Language Processing for Requirements Engineering (NLP4RE).

    [7] Sommerville, I. (2016). Software Engineering (10th ed.). Pearson Education.

    [8] Wiegers, K. E., & Beatty, J. (2013). Software Requirements (3rd ed.). Microsoft Press.

    [9] Robertson, S., & Robertson, J. (2012). Mastering the Requirements Process: Getting Requirements Right (3rd ed.). Addison-Wesley.

    [10] Hull, E., Jackson, K., & Dick, J. (2011). Requirements Engineering (3rd ed.). Springer.

    [11] Pohl, K. (2010). Requirements Engineering: Fundamentals, Principles, and Techniques. Springer.

    [12] Cohn, M. (2004). User Stories Applied: For Agile Software Development. Addison-Wesley.

    [13] Jurafsky, D., & Martin, J. H. (2019). Speech and Language Processing (3rd ed. draft). Pearson.

    [14] Russell, S., & Norvig, P. (2016). Artificial Intelligence: A Modern Approach (3rd ed.). Pearson.

    [15] Buitelaar, P., Cimiano, P., & Magnini, B. (2005). Ontology Learning from Text: Methods, Evaluation and Applications. IOS Press.

  • Downloads

Similar Articles

81-90 of 108

You may also start an advanced similarity search for this article.