Enhancing declarative business process management availability through generative AI
Open accessThe DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Abstract
Business process models serve as crucial artifacts in modern organizations, enabling stakeholders to understand, analyze, and improve their operational workflows. While traditional imperative process models are well-represented in public repositories, declarative models—particularly those capturing multiple process perspectives—remain scarce due to privacy concerns and the proprietary nature of business operations. This scarcity significantly hampers research, education, and innovation in declarative process management. We address this challenge by introducing Terpsichora, a framework that leverages large language models to generate synthetic multi-perspective declarative (MP-Declare) process models. Our strategy combines input formulation and constrained generation techniques with automated validation mechanisms to ensure the generation of diverse, realistic process models while maintaining structural validity and semantic coherence. Through comprehensive evaluation of 2000 synthetic models across two generation approaches, we demonstrate that our framework successfully generates models with diverse complexity metrics and high labeling convention compliance. The generated models effectively support various analytical tasks, including process mining and conformance checking, while preserving essential business domain characteristics. This research establishes a novel pathway for addressing the availability challenge in declarative process modeling, enabling researchers and practitioners to access diverse, high-quality process models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2024) · Business & Information Systems Engineering · doi:10.1007/s12599-023-00834-7 · Cited by 2,267
Fundamentals of Business Process Management
Dumas, M., La Rosa, M., Mendling, J., & Reijers, H. A. (2018) · Springer eBooks · doi:10.1007/978-3-662-56509-4 · Cited by 1,822 · cited 2×
“In the field of BPM, Representation Theory has been applied to evaluate and improve process models across three key dimensions (Dumas et al. 2018): 1.”
Ten Simple Rules for Reproducible Computational Research
Sandve, G. K., Nekrutenko, A., Taylor, J., & Hovig, E. (2013) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003285 · Cited by 880 · cited 1×
“Following the guidelines of (Sandve et al. 2013) in combination with the proposal of (Ivie and Thain 2018), we created an environment that promotes reproducible and replicable results 1 .”
Understanding quality in conceptual modeling
Lindland, O. I., Sindre, G., & Solvberg, A. (1994) · IEEE Software · doi:10.1109/52.268955 · Cited by 873 · cited 1×
“These metrics guide both implementation decisions and ongoing system refinement (Lindland et al. 1994).”
Seven process modeling guidelines (7PMG)
Mendling, J., Reijers, H. A., & van der Aalst, W. M. P. (2010) · Information and Software Technology · doi:10.1016/j.infsof.2009.08.004 · Cited by 626 · cited 1×
“For instance, Mendling et al. (Mendling et al. 2010) used the abstraction, isomorphism, and inference principles of this framework to develop quality metrics for process models, helping to quantify and improve model quality across these dimensions.”
DECLARE: Full Support for Loosely-Structured Processes
Pesic, M., Schonenberg, H., & van der Aalst, W. M. P. (2007) · 11th IEEE International Enterprise Distributed Object Computing Conference (EDOC 2007) · doi:10.1109/edoc.2007.14 · Cited by 561 · cited 1×
“The formal expression of these constraints has been systematically developed through many modeling languages such as Declare (Pesic et al. 2007), with MP-Declare (Burattin et al. 2016) further expanding the framework to encompass multiple process perspectives, including control-flow relationships,…”
Declarative workflows: Balancing between flexibility and support
van der Aalst, W. M. P., Pesic, M., & Schonenberg, H. (2009) · Computer Science - Research and Development · doi:10.1007/s00450-009-0057-9 · Cited by 530 · cited 2×
“The landscape of process modeling encompasses two fundamental paradigms (Der Aalst et al. 2009).”
Role play with large language models
Shanahan, M., McDonell, K., & Reynolds, L. (2023) · Nature · doi:10.1038/s41586-023-06647-8 · Cited by 491 · cited 2×
“The primary objective of this technique aligns with recent findings that LLMs can effectively embody specialized roles when given detailed agent descriptions (Xu et al. 2023; Shanahan et al. 2023).”
Role-Play with Large Language Models
Shanahan, M., McDonell, K., & Reynolds, L. (2023) · arXiv · doi:10.48550/arxiv.2305.16367 · Cited by 490 · cited 2×
“The primary objective of this technique aligns with recent findings that LLMs can effectively embody specialized roles when given detailed agent descriptions (Xu et al. 2023; Shanahan et al. 2023).”
Research works printed but not linked: 17
- Bandara W, Rosemann M (2005) What are the secrets of successful process modelling? insights from an Australian case study. Systèmes d’Information et Management 10(3):47–68
- Berti A (2024) Pm4py. llm: a comprehensive module for implementing pm on llms. arXiv preprint arXiv:2404.06035 · arXiv
- Biderman S, Schoelkopf H, Sutawika L, Gao L, Tow J, Abbasi B, Aji AF, Ammanamanchi PS, Black S, Clive J et al (2024) Lessons from the trenches on reproducible evaluation of language models. arXiv preprint arXiv:2405.14782 · arXiv
- Brachman RJ, Levesque (1985) H.J.: readings in knowledge representation. Morgan Kaufmann, Los Altos, CA
- Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry GAskell A et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 1877–1901
- Corradini F, Fornari F, Polini A, Re BTiezzi F et al (2019) Reprository: a repository platform for sharing business process models. BPM (phd/Demos) 2420:149–153
- Davies I, Rosemann M, Green P (2004) Exploring proposed ontological issues of aris with different categories of modellers. In ACIS 2004 Proceedings, vol 50
- Geng S, Josifosky M, Peyrard M, West R (2023) Flexible grammar-based constrained decoding for language models. arXiv preprint arXiv:2305.13971 · arXiv
- Green PF, Rosemann M (2002) Perceived ontological weaknesses of process modeling techniques: further evidence. In ECIS 2002 Proceedings, vol 104
- Li K, Yang S, Sullivan TM, Burd RS, Marsic I (2022) Generating privacy-preserving process data with deep generative models. arXiv preprint arXiv:2203.07949 · arXiv
- Marr D (1982) Vision: a computational investigation into the human representation and processing of visual information. W.H. Freeman and Company, San Francisco
- Recker J, Indulska M, Rosemann M, Green P (2006) How good is bpmn really? insights from theory and practice. In Proceedings of the 14th European Conference on Information Systems, IT University of Goteborg, pp. 1–12
- Recker J, Rosemann M, Indulska M, Green P (2009) Business process modeling-a comparative analysis. J Assoc Inf Syst 10(4):1
- Rosemann M, Green P (2000) Integrating multi-perspective views into ontological analysis. In Proceedings of the Twenty First International Conference on Information Systems, pp 618–627
- Skydanienko V, Di Francescomarino C, Ghidini C, Maggi FM (2018) A tool for generating event logs from multi-perspective declare models. BPM (dissertation/Demos/Industry) 2196:111–115
- Xu B, Yang A, Lin J, Wang Q, Zhou C, Zhang Y, Mao Z (2023) Expert prompting: instructing large language models to be distinguished experts. CoRr abs/2305(14688). https://doi.org/10.48550/ARXIV.2305.146882305.14688 · arXiv · doi:10.48550/arxiv.2305.146882305.14688
- Zugal S, Soffer P, Pinggera J, Weber B (2015) Dimensions of understandability in process models. In International Conference on Enterprise, Business-Process and Information Systems Modeling, pp 132–147
Cited by
Data Quality in the Age of AI: A Review of Governance, Ethics, and the FAIR Principles
Guillen-Aguinaga, M., Aguinaga-Ontoso, E., Guillen-Aguinaga, L., Guillen-Grima, F., & Aguinaga-Ontoso, I. (2025) · Data · doi:10.3390/data10120201 · Cited by 37
“The implications extend beyond compliance, as these normative instruments are reshaping market dynamics, with organizations that demonstrate robust AI governance and data quality practices gaining competitive advantages in terms of trust, market access, and regulatory alignment [254,255].”
Santos, W. D. S., Baião, F., Spyrides, G. M., & Lopes, H. (2026) · Anais Estendidos do Simpósio Brasileiro de Sistemas de Informação (SBSI) · doi:10.5753/sbsi_estendido.2026.249056
“This article presents contributions originally published as [Santos et al. 2025, da Silva Santos et al. 2025], introducing Terpsichora , a framework leveraging LLMs to generate synthetic MP-Declare models.”
Self-citationAl-Mussabi, H. S., Al-Shamsi, M. H., & Salman, S. (2026) · Student Research Conference on Applied Computing (SRC) · doi:10.1109/src70627.2026.11550709
“Due to its advantages, GANs offer a promising solution for practitioners to improve business processes and create process mining tasks without privacy concerns [15].”
Influential
Metadata
- Authors
- Santos, W. D. S., Coutinho, J. R., Baião, F., Miranda Spyrides, G., & Vieira Lopes, H. C.
- Affiliations
- Pontifícia Universidade Católica do Rio de Janeiro (BR)
- Corresponding author
- Santos, Wesley da Silva
- ORCID
- Baião, Fernanda
- Venue
- Process Science
- Published
- 2025-11-05
- Volume
- 2
- Issue
- 1
- ISSN
- 2948-2178 (ISSN-L)
- OpenAlex
- W4415906453
- Cited by
- 3
- References
- 46
- Citations by year
- 2026: 2 · 2025: 1
- FWCI
- 4.10
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-nc-nd
- creativecommons.org/licenses/by-nc-nd/4.0 (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0 (vor)
- Locations
- Process Science (publishedVersion, cc-by-nc-nd)
- Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro
- Topics
- Social Sciences › Business, Management and Accounting › Management Information Systems › Business Process Modeling and Analysis
- Physical Sciences › Computer Science › Software › Model-Driven Software Engineering Techniques
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Keywords
- large language models, generative AI, constrained generation, conformance checking, process mining
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Enhancing declarative business process management availability through generative AI. https://app.cochat.ai/papers/10.1007/s44311-025-00029-1
- The paper
- Santos, W. D. S., Coutinho, J. R., Baião, F., Miranda Spyrides, G., & Vieira Lopes, H. C. (2025). Enhancing declarative business process management availability through generative AI. Process Science. https://doi.org/10.1007/s44311-025-00029-1
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.