EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms

Francesco Granata, Francesco Poggi, Misael Mongiovì

Big Data and Cognitive Computing · 13.04.2026 · 10 (4) · 120

DOI: 10.3390/bdcc10040120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 13.04.2026. Verfasst von Francesco Granata und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Italian MIMIT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the era of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) architectures are gaining significant attention for their ability to ground language generation in reliable knowledge sources. Despite their effectiveness, RAG systems based solely on semantic similarity often fail to ensure factual accuracy in specialized domains, where terminological ambiguity can affect retrieval relevance. This study proposes Entity Linking Enhanced RAG (ELERAG), an enhanced RAG architecture that integrates a factual signal derived from Entity Linking to improve the accuracy of educational question-answering systems in Italian. The system includes a Wikidata-based Entity Linking module and implements a hybrid re-ranking strategy based on Reciprocal Rank Fusion (RRF). To validate our approach, we compared it against standard baselines and state-of-the-art methods, including a Weighted-Score Re-ranking, a standalone Cross-Encoder and a combined RRF + Cross-Encoder pipeline. Experiments were conducted on two benchmarks: a custom academic dataset and the standard SQuAD-it dataset. Results show that, in domain-specific contexts, ELERAG significantly outperforms both the baseline and the Cross-Encoder configurations. Conversely, the Cross-Encoder approaches achieve the best results on the general-domain dataset. These findings provide strong experimental evidence of the domain mismatch effect, highlighting the importance of domain-adapted hybrid strategies to enhance factual precision in educational RAG systems without relying on computationally expensive models trained on disparate data distributions. They also demonstrate the potential of entity-aware RAG systems in educational environments, fostering adaptive and reliable AI-based tutoring tools.

Förderung

  • Italian MIMIT

Zitieren

APA

Granata, F., Poggi, F., & Mongiovì, M. (2026). Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms. Big Data and Cognitive Computing, 10(4), 120. https://doi.org/10.3390/bdcc10040120

Vancouver

Granata F, Poggi F, Mongiovì M. Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms. Big Data and Cognitive Computing. 2026;10(4):120. doi:10.3390/bdcc10040120

BibTeX
@article{Granata2026,
  author = {Granata, Francesco and Poggi, Francesco and Mongiovì, Misael},
  title = {Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {120},
  doi = {10.3390/bdcc10040120}
}
Kostenlos starten →