EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Swamped with Too Many Articles? GraphRAG Makes Getting Started Easy

Joëd Ngangmeni, Danda B. Rawat

AI · 01.03.2025 · 6 (3) · 47

DOI: 10.3390/ai6030047 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 01.03.2025. Verfasst von Joëd Ngangmeni und 1 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DoD Center of Excellence in AI/ML at Howard University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Both early researchers, such as new graduate students, and experienced researchers face the challenge of sifting through vast amounts of literature to find their needle in a haystack. This process can be time-consuming, tedious, or frustratingly unproductive.

Methods

Using only abstracts and titles of research articles, we compare three retrieval methods—Bibliographic Indexing/Databasing (BI/D), Retrieval-Augmented Generation (RAG), and Graph Retrieval-Augmented Generation (GraphRAG)—which reportedly offer promising solutions to these common challenges. We assess their performance using two sets of Large Language Model (LLM)-generated queries: one set of queries with context and the other set without context. Our study evaluates six sub-models—four from Light Retrieval-Augmented Generation (LightRAG) and two from Microsoft’s Graph Retrieval-Augmented Generation (MGRAG). We examine these sub-models across four key criteria—comprehensiveness, diversity, empowerment, and directness—as well as the overall combination of these factors.

Results

After three separate experiments, we observe that MGRAG has a slight advantage over LightRAG, naïve RAG, and BI/D for answering queries that require a semantic understanding of our data pool. The results (displayed in grouped bar charts) provide clear and accessible comparisons to help researchers quickly make informed decisions on which method best suits their needs.

Conclusions

Supplementing BI/D with RAG or GraphRAG pipelines would positively impact the way both beginners and experienced researchers find and parse through volumes of potentially relevant information.

Förderung

  • DoD Center of Excellence in AI/ML at Howard University

Zitieren

APA

Ngangmeni, J., & Rawat, D. B. (2025). Swamped with Too Many Articles? GraphRAG Makes Getting Started Easy. AI, 6(3), 47. https://doi.org/10.3390/ai6030047

Vancouver

Ngangmeni J, Rawat DB. Swamped with Too Many Articles? GraphRAG Makes Getting Started Easy. AI. 2025;6(3):47. doi:10.3390/ai6030047

BibTeX
@article{Ngangmeni2025,
  author = {Ngangmeni, Joëd and Rawat, Danda B.},
  title = {Swamped with Too Many Articles? GraphRAG Makes Getting Started Easy},
  journal = {AI},
  year = {2025},
  volume = {6},
  number = {3},
  pages = {47},
  doi = {10.3390/ai6030047}
}
Kostenlos starten →