2026-08-10T22:48:22Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:24464 2025-10-13T12:16:06Z ddc:004 open_access

Prompting LLMs for the Run-Time Event Calculus (Short Paper) Kouvaras, Andreas Mantenoglou, Periklis Artikis, Alexander Event Calculus temporal pattern matching composite event recognition 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. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Andreas Kouvaras and Periklis Mantenoglou and Alexander Artikis 2025 Is Part Of LIPIcs, Volume 355, 32nd International Symposium on Temporal Representation and Reasoning (TIME 2025) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.TIME.2025.18 urn:nbn:de:0030-drops-244641 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.TIME.2025.18 eng https://creativecommons.org/licenses/by/4.0/legalcode