Discovering inconsistencies in documents with long-context LLMs

Lade...
Vorschaubild
Autor:in (Körperschaft)
Publikationsdatum
2025
Typ der Arbeit
Studiengang
Typ
04B - Beitrag Konferenzschrift
Herausgeber:in (Körperschaft)
Betreuer:in
Übergeordnetes Werk
Advanced Information Systems Engineering Workshops. CAiSE 2025 Workshops, Vienna, Austria, June 16–20, 2025, Proceedings
Themenheft
Link
Zugehörige Forschungsdaten
Reihe / Serie
Reihennummer
Jahrgang / Band
Ausgabe / Nummer
Seiten / Dauer
105-116
Patentnummer
Verlag / Herausgebende Institution
Springer
Verlagsort / Veranstaltungsort
Cham
Auflage
Version
Programmiersprache
Abtretungsempfänger:in
Praxispartner:in/Auftraggeber:in
Zusammenfassung
The increasing complexity and scale of technical document corpora present challenges for consistency verification, particularly in politically sensitive or high-stakes contexts. This paper proposes an iterative approach that integrates long-context large language models (LLMs), human expertise, and hybrid clustering mechanisms to address these challenges. The approach focuses on two types of inconsistencies: real inconsistencies, such as contradictory statements or omissions, and fabricated inconsistencies, which are plausible yet artificially introduced.This paper uses the Swiss National Cooperative for the Disposal of Radioactive Waste (Nagra) and its corpus of up to 300 technical documents as a case study. Experimental results suggest that targeted structuring of document contexts improves recall in inconsistency detection. The findings highlight the potential of combining structured human input with LLM-based reasoning for improving document integrity and trustworthiness. Future work will focus on refining the approach, including automated clustering strategies and optimization of prompt engineering.
Schlagwörter
Fachgebiet (DDC)
Projekt
Veranstaltung
International Conference on Advanced Information Systems Engineering
Startdatum der Ausstellung
Enddatum der Ausstellung
Startdatum der Konferenz
Enddatum der Konferenz
Datum der letzten Prüfung
ISBN
978-3-031-94931-9
978-3-031-94930-2
ISSN
Sprache
Englisch
Während FHNW Zugehörigkeit erstellt
Ja
Zukunftsfelder FHNW
Publikationsstatus
Veröffentlicht
Begutachtung
publication.page.reviewtype.Peer-Reviewed
Open Access-Status
Closed
Lizenz
Zitation
Martin, A., Witschel, H. F., Stockhecke, M., Nydegger, P., & Buga, K. (2025). Discovering inconsistencies in documents with long-context LLMs. In J. Grabis & Y. Wautelet (Eds.), Advanced Information Systems Engineering Workshops. CAiSE 2025 Workshops, Vienna, Austria, June 16–20, 2025, Proceedings (pp. 105–116). Springer. https://doi.org/10.1007/978-3-031-94931-9_9