EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluating Vector-Based Search and Question Answering Approaches for an Information System

Michael Dembach, Sophie Decher

Open Conference Proceedings · 23.03.2026 · 9

DOI: 10.52825/ocp.v9i.3306 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Open Conference Proceedings, online erschienen am 23.03.2026. Verfasst von Michael Dembach und 1 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Projektträger Jülich.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents two experiments conducted within the context of an information system. First, it evaluates the potential of vector-based document retrieval in contrast to ontology-based query expansion using a manually curated categorization scheme that is employed in actual practice rather than being constructed specifically for the experiment. Second, it compares the output of a RAG system to that of a group of human domain experts. The findings reveal that a vector-based approach is more effective for this use case and that RAG-generated texts may be able to stylistically compete with those of experts though content needs to be checked.

Förderung

  • Projektträger Jülich

Zitieren

APA

Dembach, M., & Decher, S. (2026). Evaluating Vector-Based Search and Question Answering Approaches for an Information System. Open Conference Proceedings, 9. https://doi.org/10.52825/ocp.v9i.3306

Vancouver

Dembach M, Decher S. Evaluating Vector-Based Search and Question Answering Approaches for an Information System. Open Conference Proceedings. 2026;9. doi:10.52825/ocp.v9i.3306

BibTeX
@article{Dembach2026,
  author = {Dembach, Michael and Decher, Sophie},
  title = {Evaluating Vector-Based Search and Question Answering Approaches for an Information System},
  journal = {Open Conference Proceedings},
  year = {2026},
  volume = {9},
  doi = {10.52825/ocp.v9i.3306}
}
Kostenlos starten →