Large Language Models in Requirements Engineering: A Literature Review
Abstract
Existen diferentes propuestas en la literatura sobre la aplicación de modelos y herramientas de Procesamiento del Lenguaje Natural – PNL para abordar las actividades y desafíos que surgen en el proceso de Ingeniería de Requerimientos – IR. En los últimos años, la Inteligencia Artificial – IA generativa implementada mediante Grandes Modelos de Lenguaje – LLMs ha ganado un importante reconocimiento debido a las notables mejoras presentadas en las tareas de PNL. Este artículo presenta un Mapeo Sistemático de la Literatura – MSL que reúne las investigaciones que proponen el uso de LLM para mejorar el proceso y resolver problemas presentes en la IR. Los resultados obtenidos muestran propuestas alentadoras dirigidas principalmente a la creación de diferentes tipos de modelos y clasificación de requerimientos. Sin embargo, todavía necesitan más desarrollo y validación empírica para ser ampliamente aceptadas y aplicadas en entornos de desarrollo de software. En consecuencia, esta situación denota la necesidad de seguir investigando y profundizando en posibles aplicaciones de los LLMs en IR.
References
Abualhaija, S., Arora, C., Sleimi, A., & Briand, L. C. (2022). Automated question Answering for improved understanding of compliance requirements: A multi-document study. 2022 IEEE 30th International Requirements Engineering Conference (RE), 15-19 August 2022, Melbourne, Australia (págs. 39 - 50). IEEE. https://doi.org/10.1109/RE54965.2022.00011
Arulmohan, S., Meurs, M.-J., & Mosser, S. (2023). Extracting domain models from textual requirements in the era of large language models. 2023 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C) (págs. 580 - 587). Västerås, Suecia: IEEE Press. https://doi.org/10.1109/MODELS-C59198.2023.00096
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., . . . Liang, P. (12 de Julio de 2022). Onthe opportunities and risks of foundation models. arXiv, 2108.07258v3 [cs.LG], 1-214. https://doi.org/10.48550/arXiv.2108.07258
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., . . . Amodei, D. (2020). Language models are few-shot learners. En H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Ed.), Advances in Neural Information Processing Systems, 34th Conference on Neural Information Processing Systems (NeurIPS 2020). 33, págs. 1877 - 1901. Vancouver, Canada: Curran Associates Inc. Obtenido de https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
Chatterjee, R., Ahmed, A., Anish, P. R., Suman, B., Lawhatre, P., & Ghaisas, S. (2021). A pipeline for automating labeling to prediction in classification of NFRs. 2021 IEEE 29th International Requirements Engineering Conference (RE), 20-24 September 2021, Notre Dame, IN, USA (págs. 323 - 323). IEEE. https://doi.org/10.1109/RE51729.2021.00036
Chen, B., Chen, K., Hassani, S., Yang, Y., Amyot, D., Lessard, L., . . . Varró, D. (2023). On the use of GPT-4 for creating goal models: An exploratory study. 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW), 04-05 September 2023, Hannover, Alemania (págs. 262 - 271). IEEE. https://doi.org/10.1109/REW57809.2023.00052
Cosler, M., Hahn, C., Mendoza, D., Schmitt, F., & Trippel, C. (2023). nl2spec: Interactively translating unstructured natural language to temporal logics with large language models. En C. Enea, & A. Lal (Ed.), Computer Aided Verification. CAV 2023. Lecture Notes in Computer Science, vol. 13965 (págs. 383 - 396). Suiza: Springer Nature. https://doi.org/10.1007/978-3-031-37703-7_18
Cruciani, F., Moore, S., & Nugent, C. (2023). Comparing general purpose pre-trained word and sentence embeddings for requirements classification. En A. Ferrari, B. Penzenstadler, I. Hadar, S. Oyedeji, S. Abualhaija, A. Vogelsang, . . . D. Amyot (Ed.), Joint Proceedings of REFSQ-2023 Workshops, Doctoral Symposium, Posters & Tools Track, and Journal Early Feedback Track. Co-located with REFSQ 2023, April 17. 3378. Barcelona, Cataluña, España: CEUR-WS.org. Obtenido de https://ceur-ws.org/Vol-3378/NLP4RE-paper4.pdf
DAIR.AI. (23 de Abril de 2023). Elements of a Prompt. Obtenido de Prompt Engineering Guide: https://www.promptingguide.ai/introduction/elements
De Vito, G., Palomba, F., Gravino, C., Di Martino, S., & Ferrucci, F. (2023). ECHO: An approach to enhance use case quality exploiting large language models. 2023 49th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), 06-08 September 2023 (págs. 53 - 60). Durres, Albania: IEEE. https://doi.org/10.1109/SEAA60479.2023.00017
Devine, P., Koh, Y. S., & Blincoe, K. (2023). Evaluating software user feedback classifier performance on unseen apps, datasets, and metadata. Empirical Software Engineering, 28, 26. https://doi.org/10.1007/s10664-022-10254-y
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. En J. Burstein, C. Doran, & T. Solorio (Ed.), Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 1, págs. 4171 - 4186. Minneapolis, Minnesota, USA: Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-142
Ezzini, S., Abualhaija, S., Arora, C., & Sabetzadeh, M. (2022). Automated handling of anaphoric ambiguity in requirements: A multi-solution study. 44th IEEE/ACM 44th International Conference on Software Engineering, {ICSE} 2022, May 25-27 (págs. 187 - 199). Pittsburgh, PA, USA: ACM. https://doi.org/10.1145/3510003.3510157
Ezzini, S., Abualhaija, S., Arora, C., & Sabetzadeh, M. (2023). AI-based question answering assistance for analyzing natural-language requirements. 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 14-20 May 2023 (págs. 1277 - 1289). Melbourne, Australia: IEEE. https://doi.org/10.1109/ICSE48619.2023.00113
Fengli, X., Hao, Q., Shao, C., Zong, Z., Li, Y., Wang, J., . . . Yong, L. (10 de Octubre de 2025). Toward large reasoning models: A survey of reinforced reasoning with large language models. Patterns, 6(10), 1 - 30, 101370. https://doi.org/10.1016/j.patter.2025.101370
Görer, B., & Aydemir, F. B. (2023). Generating requirements elicitation interview scripts with large language models. 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW). 04-05 September 2023 (págs. 44 - 51). Hannover, Alemania: IEEE. https://doi.org/10.1109/REW57809.2023.00015
Gramajo, M. G., Ballejos, L., & Ale, M. (Julio de 2020). Seizing requirements engineering issues through supervised learning techniques. IEEE Latin America Transactions, 18(07), 1164 - 1184. https://doi.org/10.1109/TLA.2020.9099757
Hadi, M. U., Al-Tashi, Q., Qureshi, R., Shah, A., Muneer, A., Irfan, M., . . . Shah, M. (10 de Febrero de 2025). Large language models: A comprehensive survey of its applications, challenges, limitations, and future prospects. TechRxiv, 1-54. https://doi.org/10.36227/techrxiv.23589741.v8
Han, W., Xiang, W., Cui, X., Cheng, N., Jiang, G., Qian, W., & Zhang, C. (2025). Prompt engineering 101: Prompt engineering guidelines from a linguistic perspective. En M. Sun, J. Liang, X. Han, Z. Liu, Y. He, G. Rao, . . . Z. Tian (Ed.), Chinese Computational Linguistics. CCL 2024. Lecture Notes in Computer Science (LNAI, volume 14761) (págs. 571 - 592). Singapur: Springer Nature. https://doi.org/10.1007/978-981-97-8367-0_34
Jain, C., Anish, P. R., Singh, A., & Ghaisas, S. (2023). A transformer-based approach for abstractive summarization of requirements from obligations in software engineering contracts. 2023 IEEE 31st International Requirements Engineering Conference (RE), 04-08 September 2023 (págs. 169 - 179). Hannover, Alemania: IEEE. https://doi.org/10.1109/RE57278.2023.00025
Jin, D., Jin, Z., Chen, X., & Wang, C. (2024). ChatModeler: A human-machine collaborative and iterative requirements elicitation and modeling approach via large language models. Journal of Computer Research and Development, 61(2), 338 - 350. https://doi.org/10.7544/issn1000-1239.202330746
Kitchenham, B., & Charters, S. M. (2007). Guidelines for performing systematic literature reviews in software engineering. Version 2.3. EBSE Technical Report EBSE-2007-01, Keele University, y University of Durham. Obtenido de https://legacyfileshare.elsevier.com/promis_misc/525444systematicreviewsguide.pdf
Li, Y. (2023). A practical survey on zero-shot prompt design for In-context learning. En R. Mitkov, & G. Angelova (Ed.), Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing (págs. 641 - 647). Varna, Bulgaria: INCOMA Ltd. Obtenido de https://aclanthology.org/2023.ranlp-1.69/
Lyu, Y., Yan, L., Wang, S., Shi, H., Yin, D., Ren, P., . . . Ren, Z. (2024). KnowTuning: Knowledge-aware fine-tuning for Large Language Models. En Y. Al-Onaizan, M. Bansal, & Y.-N. Chen (Ed.), Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (págs. 14535 - 14556). Miami, Florida, USA: Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.emnlp-main.805
Mendes, E., Wohlin, C., Felizardo, K., & Kalinowski, M. (Septiembre de 2020). When to update systematic literature reviews in software engineering. Journal of Systems and Software, 167, 110607. https://doi.org/10.1016/j.jss.2020.110607
Molla, Y. S., Yimer, S. T., & Alemneh, E. (2023). COSMIC - functional size classification of agile software development: Deep learning approach. En 2023 (Ed.), 2023 International Conference on Information and Communication Technology for Development for Africa (ICT4DA), 26-28 October 2023, Bahir Dar, Etiopia (págs. 155 - 159). IEEE. https://doi.org/10.1109/ICT4DA59526.2023.10302232
Nadeem, A., Sarwar, M. U., & Malik, M. Z. (2021). Automatic issue classifier: A transfer learning framework for classifying issue reports. 2021 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW), 25-28 October 2021, Wuhan, China (págs. 421 - 426). IEEE. https://doi.org/10.1109/ISSREW53611.2021.00113
Nakagawa, H., & Honiden, S. (2023). MAPE-K loop-based goal model generation using generative AI. En K. Schneider, F. Dalpiaz, & J. Horkoff (Ed.), Proceedings - 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW), 04-05 September 2023, Hannover, Alemania (págs. 247 - 251). IEEE. https://doi.org/10.1109/REW57809.2023.00050
Nuseibeh, B., & Easterbrook, S. (2000). Requirements engineering: a roadmap. ICSE '00: Proceedings of the Conference on The Future of Software Engineering (págs. 35 - 46). Limerick, Ireland: Association for Computing Machinery - ACM. https://doi.org/10.1145/336512.336523
OpenAI. (28 de Abril de 2025). OpenAI. Obtenido de sitio web de OpenAI: https://openai.com/
Patil, R., & Gudivada, V. (Marzo de 2024). A review of current trends, techniques, and challenges in Large Language Models (LLMs). Applied Sciences, 14(5). https://doi.org/10.3390/app14052074
Petersen, K., Feldt, R., Mujtaba, S., & Mattsson, M. (2008). Systematic mapping studies in software engineering. 12th International Conference on Evaluation and Assessment in Software Engineering (EASE), 26 - 27 June 2008 (págs. 68 - 77). Bari, Italy: BCS Learning and Development Ltd. https://doi.org/10.14236/ewic/EASE2008.8
Petersen, K., Vakkalanka, S., & Kuzniarz, L. (Agosto de 2015). Guidelines for conducting systematic mapping studies in software engineering: An update. Information and Software Technology, 64, 1 - 18. https://doi.org/10.1016/j.infsof.2015.03.007
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., . . . Liu, P. J. (Enero de 2020). Exploring the limits of transfer learning with a unified text-to-text transformer. (I. Titov, Ed.) Journal of Machine Learning Research, 21(1), 5485 - 5551, Art. No. 140. Obtenido de https://jmlr.org/papers/volume21/20-074/20-074.pdf
Rahimi, N., Eassa, F., & Elrefaei, L. (2020). An ensemble machine learning technique for functional requirement classification. Symmetry, 12(10), 1601. https://doi.org/10.3390/sym12101601
Raiaan, M. A., Mukta, S. H., Fatema, K., Fahad, N. M., Sakib, S., Mim, M. M., . . . Azam, S. (2024). A review on large language models: Architectures, applications, taxonomies, open issues and challenges. IEEE Access, 12, 26839 - 26874. https://doi.org/10.1109/ACCESS.2024.3365742
Rejithkumar, G., Anish, P. R., & Ghaisas, S. (2023). Automated Identification of Deontic Modalities in Software Engineering Contracts: A Domain Adaptation-Based Generative Approach. 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW), 4-5 September 2023, Hannover, Alemania (págs. 72 - 75). Los Alamitos, CA, USA: IEEE Computer Society. https://doi.org/10.1109/REW57809.2023.00020
Restrepo Henao, P., Fischbach, J., Spies, D., Frattini, J., & Vogelsang, A. (2021). Transfer learning for mining feature requests and bug reports from tweets and app store reviews. 2021 IEEE 29th International Requirements Engineering Conference Workshops (REW), Notre Dame, IN, USA (págs. 80 - 86). Los Alamitos, CA, USA: IEEE Computer Society. https://doi.org/10.1109/REW53955.2021.00019
Ronanki, K., Berger, C., & Horkoff, J. (2023). Investigating ChatGPT’s potential to assist in requirements elicitation processes. 2023 49th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), 06-08 September 2023 (págs. 354 - 361). Durres, Albania: IEEE. https://doi.org/10.1109/SEAA60479.2023.00061
Ruan, K., Chen, X., & Jin, Z. (2023). Requirements modeling aided by ChatGPT: An experience in embedded systems. 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW), 04-05 September 2023, Hannover, Alemania (págs. 170 - 177). IEEE. https://doi.org/10.1109/REW57809.2023.00035
Sainani, A., Anish, P. R., Joshi, V., & Ghaisas, S. (2020). Extracting and classifying requirements from software engineering contracts. 2020 IEEE 28th International Requirements Engineering Conference (RE), 31 August 2020 - 04 September, Zurich, Suiza (págs. 147 - 157). IEEE. https://doi.org/10.1109/RE48521.2020.00026
Sihag, M., Li, Z. S., Dash, A., Arony, N. N., Devathasan, K., Ernst, N., . . . Daniela, D. (2023). A data-driven approach for finding requirements relevant feedback from TikTok and YouTube. 2023 IEEE 31st International Requirements Engineering Conference (RE), 04-08 September 2023, Hannover, Alemania (págs. 111 - 122). IEEE. https://doi.org/10.1109/RE57278.2023.00020
Sommerville, I. (2011). Software engineering (9th ed.). Addison-Wesley. Obtenido de https://engineering.futureuniversity.com/BOOKS%20FOR%20IT/Software-Engineering-9th-Edition-by-Ian-Sommerville.pdf
Stanik, C., Pietz, T., & Maalej, W. (2021). Unsupervised topic discovery in user comments. 2021 IEEE 29th International Requirements Engineering Conference (RE), Notre Dame, IN, USA (págs. 150 - 161). Los Alamitos, CA, USA: IEEE Computer Society. https://doi.org/10.1109/RE51729.2021.00021
Tikayat Ray, A., Cole, B. F., Pinon Fischer, O. J., Bhat, A. P., White, R. T., & Mavris, D. N. (2023). Agile methodology for the standardization of engineering requirements using large language models. Systems, 11(7), 352. https://doi.org/10.3390/systems11070352
Tizard, J., Devine, P., Wang, H., & Blincoe, K. (1 de Abril de 2023). A software requirements ecosystem: linking forum, issue tracker, and FAQs for requirements management. IEEE Transactions on Software Engineering, 49(4), 2381 - 2393. https://doi.org/10.1109/TSE.2022.3219458
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., . . . Polosukhin, I. (2017). Attention is all you need. En I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Ed.), Advances in Neural Information Processing Systems. 31st Conference on Neural Information Processing Systems (NIPS 2017). 30, págs. 1-11. Long Beach, CA, USA: Curran Associates Inc. Obtenido de https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Wang, Y., Shi, L., Li, M., & Wang, Q. (2020). A deep context-wise method for coreference detection in natural language requirements. 2020 IEEE 28th International Requirements Engineering Conference (RE), 31 August 2020 - 04 September (págs. 180 - 191). Zurich, Suiza: IEEE. https://doi.org/10.1109/RE48521.2020.00029
Wei, J., Courbis, A.-L., Lambolais, T., Xu, B., Bernard, P. L., & Dray, G. (2023). Zero-shot bilingual app reviews mining with large language models. 2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI), Atlanta, GA, USA (págs. 898 - 904). Los Alamitos, CA, USA: IEEE Computer Society. https://doi.org/10.1109/ICTAI59109.2023.00135
Wikipedia. (28 de Enero de 2024). Wikipedia. Obtenido de Sitio web de Wikipedia: https://www.wikipedia.org/
Xia, Y., Zhai, S., Wang, Q., Hou, H., Wu, Z., & Shen, Q. (2022). Automated extraction of ABAC policies from natural-language documents in healthcare systems. 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 06-08 December 2022, Las Vegas, NV, USA (págs. 1289 - 1296). IEEE. https://doi.org/10.1109/BIBM55620.2022.9995559
Zhang, J., Chen, Y., Liu, C., Niu, N., & Wang, Y. (2023). Empirical evaluation of ChatGPT on requirements information retrieval under zero-shot setting. 2023 International Conference on Intelligent Computing and Next Generation Networks（ICNGN), 17-18 November 2023, Hangzhou, China (págs. 1 - 6). IEEE. https://doi.org/10.1109/ICNGN59831.2023.10396810
Zhang, W., Wang, X., Lai, S., Ye, C., & Zhou, H. (2022). Fine-tuning pre-trained model to extract undesired behaviors from app reviews. 2022 IEEE 22nd International Conference on Software Quality, Reliability and Security (QRS), 05-09 December 2022, Guangzhou, China (págs. 1125 - 1134). IEEE. https://doi.org/10.1109/QRS57517.2022.00115
Zhu, R., Li, W., & Jin, C. (2023). TAG: UML activity diagram deeply supervised generation from business textural specification. 2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 21-24 March 2023, Taipa, Macao (págs. 956 - 961). Los Alamitos, CA, USA: IEEE Computer Society. https://doi.org/10.1109/SANER56733.2023.00116
Downloads
Copyright (c) 2026 Revista Colombiana de Computación
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
