Enhancing Declarative Business Process Management Availability Through Generative AI Extended Abstract – CTDG-SI 2026

• Wesley da Silva Santos PUC-Rio / Inteli
• Fernanda Baião UFRJ
• Georges Miranda Spyrides PUC-Rio
• Hélio Cortês Vieira Lopes PUC-Rio

DOI: https://doi.org/10.5753/sbsi_estendido.2026.249056

Resumo

This work addresses the scarcity of multi-perspective declarative process models caused by privacy constraints and formalism adoption by introducing Terpsichora, a framework utilizing Large Language Models (LLM) for synthetic generation. Aligned with the “Grand Challenges of Information Systems Research in Brazil” (GranDSI-BR) 2016-2026, it bridges openness and privacy through synthetic artifacts for public benchmarking, tackles multi-perspective modeling across diverse domains, and evaluates cognitive comprehensibility. Validated through Representation Theory, the 2,000 produced models confirm syntactic rigor, semantic accuracy, and pragmatic validity.

Referências

Abbad-Andaloussi, A., Burattin, A., Slaats, T., Kindler, E., and Weber, B. (2023). Complexity in declarative process models: Metrics and multi-modal assessment of cognitive load. Expert Systems with Applications, 233:120924.

Alman, A., Donadello, I., Maggi, F. M., and Montali, M. (2023). Declarative process mining for software processes: The rum toolkit and the declare4py python library. In International Conference on Product-Focused Software Process Improvement, pages 13–19. Springer.

Boscarioli, C., de Araujo, R. M., and Maciel, R. S. P. (2017). I grandsi-br grand research challenges in information systems in brazil 2016-2026.

Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.

Burattin, A., Maggi, F. M., and Sperduti, A. (2016). Conformance checking based on multi-perspective declarative process models. Expert Systems with Applications, 65:194–211.

Corradini, F., Fornari, F., Polini, A., Re, B., Tiezzi, F., et al. (2019). Reprository: a repository platform for sharing business process models. BPM (PhD/Demos), 2420:149–153.

da Silva Santos, W., Coutinho, J. R., Baião, F., Spyrides, G. M., and Lopes, H. C. V. (2025). Terpsichora: A tool to generate synthetic mp-declare process models. In Delgado, A. and Slaats, T., editors, Process Mining Workshops, pages 624–636, Cham. Springer Nature Switzerland.

Feuerriegel, S., Hartmann, J., Janiesch, C., and Zschech, P. (2024). Generative ai. Business & Information Systems Engineering, 66(1):111–126.

Leopold, H., Eid-Sabbagh, R.-H., Mendling, J., Azevedo, L. G., and Baiao, F. A. (2013). Detection of naming convention violations in process models for different languages. Decision Support Systems, 56:310–325.

Martino, A., Iannelli, M., and Truong, C. (2023). Knowledge injection to counter large language model (llm) hallucination. In European Semantic Web Conference, pages 182–185. Springer.

Santos, W. d. S., Coutinho, J. R., Baião, F., Miranda Spyrides, G., and Vieira Lopes, H. C. (2025). Enhancing declarative business process management availability through generative ai. Process Science, 2(1):21.

Shanahan, M., McDonell, K., and Reynolds, L. (2023). Role play with large language models. Nature, 623(7987):493–498.

van Der Aalst, W. M., Pesic, M., and Schonenberg, H. (2009). Declarative workflows: Balancing between flexibility and support. Computer Science-Research and Development, 23:99–113.

Weber, R. and Lybrand, C. . (1997). Ontological Foundations of Information Systems. Coopers & Lybrand accounting research methodology monograph. Coopers & Lybrand and the Accounting Association of Australia and New Zealand.