Abstract
Organizations are obliged to ensure compliance with an increasing amount of regulatory requirements stemming from laws, regulations, directives, and policies. As a first step, it is to be determined which of the requirements are relevant in a certain context, depending on factors such as location of the organization and the business processes. For the processes, the identification of relevant requirements can be detailed by an assessment of which parts of each document are relevant for which step of a given process. Nowadays the identification of process-relevant regulatory requirements is mostly done manually by domain and legal experts, posing a tremendous workload due to the extensive number of regulatory documents and their frequent changes. Hence, this work examines how organizations can be assisted in the identification of relevant requirements for their processes based on embedding-based NLP ranking and generative AI. The evaluation highlights strengths and weaknesses of both methods regarding applicability, automation, transparency, and reproducibility. The evaluation results lead to guidelines on which method combinations will maximize benefits for given characteristics such as process usage, impact, and dynamics of an application scenario.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
References
van der Aa, H., Leopold, H., Reijers, H.A.: Checking process compliance against natural language specifications using behavioral spaces. Inf. Syst. 78, 83–95 (2018)
Althammer, S., Askari, A., Verberne, S., Hanbury, A.: Dossier@coliee 2021: Leveraging dense retrieval and summarization-based re-ranking for case law retrieval (2021)
Askari, A., Abolghasemi, A., Pasi, G., Kraaij, W., Verberne, S.: Injecting the BM25 score as text improves Bert-based re-rankers. In: ECIR Conference (2023)
Busch, K., Rochlitzer, A., Sola, D., Leopold, H.: Just tell me: prompt engineering in business process management. In: BPMDS Conference, pp. 3–11 (2023)
Dimlioglu, T., et al.: Automatic document classification via transformers for regulations compliance management in large utility companies. Neural Comput. Appl. 35, 17167–17185 (2023)
Dragoni, M., Villata, S., Rizzi, W., Governatori, G.: Combining natural language processing approaches for rule extraction from legal documents. In: AICOL Workshops (2018)
Goebel, R., Kano, Y., Kim, M., Rabelo, J., Satoh, K., Yoshioka, M.: Summary of the competition on legal information, extraction/entailment (COLIEE) 2023. In: ICAIL Conference, pp. 472–480 (2023)
Gordon, D.G., Breaux, T.D.: The role of legal expertise in interpretation of legal requirements and definitions. In: IEEE Requirements Engineering Conference, pp. 273–282 (2014)
Governatori, G., Hoffmann, J., Sadiq, S.W., Weber, I.: Detecting regulatory compliance for business process models through semantic annotations. In: BPM Workshop, pp. 5–17 (2008)
Governatori, G., Sadiq, S.W.: The journey to business process compliance. In: Handbook of Research on Business Process Modeling, pp. 426–454 (2009)
Hashmi, M., Governatori, G., Wynn, M.T.: Normative requirements for regulatory compliance: an abstract formal framework. Inf. Syst. Front. 18, 429–455 (2016)
Hliaoutakis, A., Varelas, G., Voutsakis, E., Petrakis, E.G.M., Milios, E.E.: Information retrieval by semantic similarity. Int. J. Semant. Web Inf. Syst. 2, 55–73 (2006)
Huang, F., Kwak, H., An, J.: Is ChatGPT better than human annotators? potential and limitations of ChatGPT in explaining implicit hate speech. In: ACM Web Conference, pp. 294–297 (2023)
Jiang, Z., Xu, F.F., Araki, J., Neubig, G.: How can we know what language models know. Trans. Assoc. Comput. Linguist. 8, 423–438 (2020)
Kim, M., Rabelo, J., Goebel, R., Yoshioka, M., Kano, Y., Satoh, K.: COLIEE 2022 summary: methods for legal document retrieval and entailment. In: JSAI-isAI Workshops, pp. 51–67 (2022)
Kim, M., Rabelo, J., Okeke, K., Goebel, R.: Legal information retrieval and entailment based on bm25, transformer and semantic thesaurus methods. Rev. Socionetwork Strateg. 16, 157–174 (2022)
Klampanos, I.A.: Manning christopher, prabhakar raghavan, hinrich schütze: introduction to information retrieval. Inf. Retr. 12, 609–612 (2009)
Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. In: NeurIPS (2022)
Kuzi, S., Zhang, M., Li, C., Bendersky, M., Najork, M.: Leveraging semantic and lexical matching to improve the recall of document retrieval systems: a hybrid approach. CoRR (2020)
Leopold, H., van der Aa, H., Pittke, F., Raffel, M., Mendling, J., Reijers, H.A.: Searching textual and model-based process descriptions based on a unified data format. Softw. Syst. Model. 18, 1179–1194 (2019)
Liu, Y., et al.: Summary of ChatGPT/GPT-4 research and perspective towards the future of large language models. CoRR (2023)
Looy, A.V., Backer, M.D., Poels, G., Snoeck, M.: Choosing the right business process maturity model. Inf. Manag. 50, 466–488 (2013)
Ly, L.T., Maggi, F.M., Montali, M., Rinderle-Ma, S., van der Aalst, W.M.P.: Compliance monitoring in business processes: functionalities, application, and tool-support. Inf. Syst. 54, 209–234 (2015)
Nigam, S.K., Goel, N., Bhattacharya, A.: nigam@coliee-22: legal case retrieval and entailment using cascading of lexical and semantic-based models. In: JSAI-isAI Workshops, pp. 96–108 (2022)
OpenAI: GPT-4 technical report. CoRR (2023)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: EMNLP Conference (2019)
Robertson, S.E., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr. 3, 333–389 (2009)
Sadiq, S.W., Governatori, G., Namiri, K.: Modeling control objectives for business process compliance. In: BPM Conference, pp. 149–164 (2007)
Sai, C., Winter, K., Fernanda, E., Rinderle-Ma, S.: Detecting deviations between external and internal regulatory requirements for improved process compliance assessment. In: Advanced Information Systems Engineering, pp. 1–16 (2023)
Sapkota, K., Aldea, A., Younas, M., Duce, D.A., Bañares-Alcántara, R.: Extracting meaningful entities from regulatory text: towards automating regulatory compliance. In: Workshop on Requirements Engineering and Law, pp. 29–32 (2012)
Schumann, G., Meyer, K., Gómez, J.M.: Query-based retrieval of German regulatory documents for internal auditing purposes. In: Data Science and Information Technology Conference, pp. 1–10 (2022)
Trautmann, D., Petrova, A., Schilder, F.: Legal prompt engineering for multilingual legal judgement prediction. CoRR (2022)
Winter, K., van der Aa, H., Rinderle-Ma, S., Weidlich, M.: Assessing the compliance of business process models with regulatory documents. In: Conceptual Modeling Conference, pp. 189–203 (2020). https://doi.org/10.1007/978-3-030-62522-1_14
Winter, K., Rinderle-Ma, S.: Deriving and combining mixed graphs from regulatory documents based on constraint relations. In: Advanced Information Systems Engineering, pp. 430–445 (2019)
Zhao, L., et al.: Natural language processing for requirements engineering: a systematic mapping study. ACM Comput. Surv. 54, 1–41 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sai, C., Sadiq, S., Han, L., Demartini, G., Rinderle-Ma, S. (2024). Which Legal Requirements are Relevant to a Business Process? Comparing AI-Driven Methods as Expert Aid. In: Araújo, J., de la Vara, J.L., Santos, M.Y., Assar, S. (eds) Research Challenges in Information Science. RCIS 2024. Lecture Notes in Business Information Processing, vol 513. Springer, Cham. https://doi.org/10.1007/978-3-031-59465-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-59465-6_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-59464-9
Online ISBN: 978-3-031-59465-6
eBook Packages: Computer ScienceComputer Science (R0)