Effective risk management is crucial yet challenging in modern projects because early warning signals often surface in informal, unstructured data sources and evolve as project contexts change. Since prevailing project risk management (PRM) practices largely depend on structured inputs and episodic control routines, they can miss these subtle signals, creating a temporal detection gap between risk emergence and formal identification. This paper introduces an LLM-based architecture for information extraction in PRM. Following a Design Science Research approach, we design, instantiate, and evaluate it, governed by two complementary flows: an Information Flow that continuously transforms heterogeneous project communication into structured, evidence-linked risk indicators through domain-specialized extraction and cross-source reconciliation, and an Extraction Control Flow that versions extraction behavior to remain adaptable, transparent, and auditable. We abstract four nascent design principles capturing transferable design knowledge for LLM-based information extraction in dynamic, context-rich domains.
Paetzold, Felix, Guggenberger, Tobias, Jungk, Tim et al. From weak signals to risk indicators: An LLM-based information extraction architecture for IT project risk management. // Electronic Markets. – 2026. – DOI: 10.1007/s12525-026-00928-6. – URL: http://link.springer.com/openurl/fulltext?id=doi:10.1007/s12525-026-00928-6
Paetzold, Felix, Guggenberger, Tobias, Jungk, Tim, Protschky, Dominik, Ströher, Tobias, Strüker, & Jens (2026). From weak signals to risk indicators: An LLM-based information extraction architecture for IT project risk management. Electronic Markets. https://doi.org/10.1007/s12525-026-00928-6
Paetzold, et al. “From weak signals to risk indicators: An LLM-based information extraction architecture for IT project risk management.” Electronic Markets, 2026. doi:10.1007/s12525-026-00928-6.
@article{Paetzold2026,
title = {From weak signals to risk indicators: An LLM-based information extraction architecture for IT project risk management},
author = {Paetzold and Felix and Guggenberger and Tobias and Jungk and Tim and Protschky and Dominik and Ströher and Tobias and Strüker and Jens},
journal = {Electronic Markets},
year = {2026},
doi = {10.1007/s12525-026-00928-6},
url = {http://link.springer.com/openurl/fulltext?id=doi:10.1007/s12525-026-00928-6}
}
Effective teamwork depends on teams’ ability to coordinate time. Although research distinguishes between explicit and implicit forms of team temporal coordination, relatively little is known about how these mechanisms interact to...
The Queen Elisabeth Competition is a renowned international music competition that identifies and promotes exceptional classical musicians. In each of the three rounds, a panel of judges gives numerical scores to candidates. The rule of...
In large-scale group decision making (LSGDM), traditional clustering methods typically rely on a single distance metric, ignoring both intra-cluster compactness and inter-cluster separation, and often fail to adaptively determine the...
Group decision-making (GDM) under social networks faces challenges from asymmetric interactions among decision-makers (DMs) and unconnected components. This paper proposes a consensus-reaching mechanism based on directed...
Small and medium-sized enterprises (SMEs) contribute to economic growth, employment, and innovation, yet many in fragile economies struggle to sustain financial performance. This study examines the direct relationships between...