at Google ScholarTitle data
Neuberger, Julian ; Ackermann, Lars ; van der Aa, Han ; Jablonski, Stefan:
A Universal Prompting Strategy for Extracting Process Model Information from Natural Language Text Using Large Language Models.
In: Maass, Wolfgang ; Han, Hyoil ; Yasar, Hasan ; Multari, Nick
(ed.):
Conceptual Modeling : Proceedings. -
Cham, Switzerland
: Springer Nature
,
2025
. - pp. 38-55
. - (Lecture Notes in Computer Science
; 15238
)
ISBN 978-3-031-75872-0
DOI: https://doi.org/10.1007/978-3-031-75872-0_3
Abstract in another language
Over the past decade, extensive research efforts have been dedicated to the extraction of information from textual process descriptions. Despite the remarkable progress witnessed in natural language processing (NLP), information extraction within the Business Process Management domain remains predominantly reliant on rule-based systems and machine learning methodologies. Data scarcity has so far prevented the successful application of deep learning techniques. However, the rapid progress in generative large language models (LLMs) makes it possible to solve many NLP tasks with very high quality without the need for extensive data. Therefore, we systematically investigate the potential of LLMs for extracting information from textual process descriptions, targeting the detection of process elements such as activities and actors, and relations between them. Based on a novel prompting strategy, we show that LLMs are able to outperform state-of-the-art machine learning approaches with absolute performance improvements of up to 8% $$F_1$$F1score across three different datasets. We evaluate our prompting strategy on eight different LLMs, showing it is universally applicable, while also analyzing the impact of certain prompt parts on extraction quality. The number of example texts, the specificity of definitions, and the rigour of format instructions are identified as key for improving the accuracy of extracted information. Our code, prompts, and data are publicly available at https://github.com/JulianNeuberger/llm-process-generation/tree/er2024.
Further data
| Item Type: | Article in a book |
|---|---|
| Refereed: | Yes |
| Institutions of the University: | Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Computer Science > Chair Applied Computer Science IV > Chair Applied Computer Science IV - Univ.-Prof. Dr.-Ing. Stefan Jablonski |
| Result of work at the UBT: | Yes |
| DDC Subjects: | 000 Computer Science, information, general works > 004 Computer science |
| Date Deposited: | 30 Oct 2024 11:20 |
| Last Modified: | 30 Oct 2024 11:20 |
| URI: | https://eref.uni-bayreuth.de/id/eprint/90902 |