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