Document Open Access Logo

Prompting LLMs for the Run-Time Event Calculus (Short Paper)

Authors Andreas Kouvaras , Periklis Mantenoglou , Alexander Artikis

PDF

File

Thumbnail PDF
PDF
LIPIcs.TIME.2025.18.pdf
  • Filesize: 0.67 MB
  • 7 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Computing methodologies → Temporal reasoning
Keywords
  • Event Calculus
  • temporal pattern matching
  • composite event recognition

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Abstract

Composite activity recognition systems analyse streams of low-level, symbolic events to identify instances of complex activities based on their formal definitions. Crafting these definitions is a challenging task, as it often requires specifying intricate spatio-temporal constraints, and acquiring labeled data for automated learning is difficult. To address this challenge, we introduce a method that leverages pre-trained Large Language Models (LLMs) to generate composite activity definitions, in the language of the Run-Time Event Calculus, from natural language descriptions.

Cite As Get BibTex

Andreas Kouvaras, Periklis Mantenoglou, and Alexander Artikis. Prompting LLMs for the Run-Time Event Calculus (Short Paper). In 32nd International Symposium on Temporal Representation and Reasoning (TIME 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 355, pp. 18:1-18:7, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/LIPIcs.TIME.2025.18

Author Details

Andreas Kouvaras
  • University of Piraeus, Greece
Periklis Mantenoglou
  • Örebro University, Sweden
Alexander Artikis
  • University of Piraeus, Greece
  • NCSR "Demokritos", Athens, Greece

Acknowledgements

This work was supported partly by the EU-funded project ENEXA (101070305), and partly by the Wallenberg AI, Autonomous Systems and Software Program funded by the Knut and Alice Wallenberg Foundation.

Supplementary Materials

References

  1. Elias Alevizos, Alexander Artikis, and Georgios Paliouras. Complex event recognition with symbolic register transducers. Proc. VLDB Endow., 17(11):3165-3177, 2024. URL: https://doi.org/10.14778/3681954.3681991.
  2. Alexander Artikis, Marek J. Sergot, and Georgios Paliouras. An event calculus for event recognition. IEEE Trans. Knowl. Data Eng., 27(4):895-908, 2015. URL: https://doi.org/10.1109/TKDE.2014.2356476.
  3. Alexander Artikis and Dimitris Zissis, editors. Guide to Maritime Informatics. Springer, 2021. URL: https://doi.org/10.1007/978-3-030-61852-0.
  4. Iliano Cervesato and Angelo Montanari. A calculus of macro-events: Progress report. In TIME, pages 47-58, 2000. URL: https://doi.org/10.1109/TIME.2000.856584.
  5. Luca Chittaro and Angelo Montanari. Efficient temporal reasoning in the cached event calculus. Comput. Intell., 12:359-382, 1996. URL: https://doi.org/10.1111/J.1467-8640.1996.TB00267.X.
  6. Lars George, Bruno Cadonna, and Matthias Weidlich. Il-miner: Instance-level discovery of complex event patterns. Proc. VLDB Endow., 10(1):25-36, 2016. URL: https://doi.org/10.14778/3015270.3015273.
  7. Nikos Giatrakos, Elias Alevizos, Alexander Artikis, Antonios Deligiannakis, and Minos N. Garofalakis. Complex event recognition in the big data era: a survey. VLDB J., 29(1):313-352, 2020. URL: https://doi.org/10.1007/S00778-019-00557-W.
  8. Alejandro Grez, Cristian Riveros, Martín Ugarte, and Stijn Vansummeren. A formal framework for complex event recognition. ACM Trans. Database Syst., 46(4):16:1-16:49, 2021. URL: https://doi.org/10.1145/3485463.
  9. Nikos Katzouris, Georgios Paliouras, and Alexander Artikis. Online learning probabilistic event calculus theories in answer set programming. Theory Pract. Log. Program., 23(2):362-386, 2023. URL: https://doi.org/10.1017/S1471068421000107.
  10. R. Kowalski and M. Sergot. A logic-based calculus of events. New Gen. Computing, 4(1):67-96, 1986. URL: https://doi.org/10.1007/BF03037383.
  11. Periklis Mantenoglou and Alexander Artikis. Extending the range of temporal specifications of the run-time event calculus. In TIME, volume 318, pages 6:1-6:14, 2024. URL: https://doi.org/10.4230/LIPICS.TIME.2024.6.
  12. Periklis Mantenoglou and Alexander Artikis. Temporal specification optimisation for the event calculus. In AAAI-25, pages 15075-15082, 2025. URL: https://doi.org/10.1609/AAAI.V39I14.33653.
  13. Periklis Mantenoglou, Dimitrios Kelesis, and Alexander Artikis. Complex event recognition with allen relations. In KR, pages 502-511, 2023. URL: https://doi.org/10.24963/KR.2023/49.
  14. Periklis Mantenoglou, Manolis Pitsikalis, and Alexander Artikis. Stream reasoning with cycles. In KR, pages 544-553, 2022. Google Scholar
  15. Evangelos Michelioudakis, Alexander Artikis, and Georgios Paliouras. Online semi-supervised learning of composite event rules by combining structure and mass-based predicate similarity. Mach. Learn., 113(3):1445-1481, 2024. URL: https://doi.org/10.1007/S10994-023-06447-1.
  16. Georgios M. Santipantakis, Akrivi Vlachou, Christos Doulkeridis, Alexander Artikis, Ioannis Kontopoulos, and George A. Vouros. A stream reasoning system for maritime monitoring. In TIME, volume 120, pages 20:1-20:17, 2018. URL: https://doi.org/10.4230/LIPICS.TIME.2018.20.
  17. Walker M. White, Mirek Riedewald, Johannes Gehrke, and Alan J. Demers. What is "next" in event processing? In PODS, pages 263-272, 2007. URL: https://doi.org/10.1145/1265530.1265567.
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact