Fine-tuning or prompting on LLMs: evaluating knowledge graph construction task
Frontiers in Big Data · 25.06.2025 · 8
DOI: 10.3389/fdata.2025.1505877 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Big Data, online erschienen am 25.06.2025. Verfasst von Hussam Ghanem und 1 weiteren Autor:innen. Beteiligte Einrichtung: Université Bourgogne Europe, CNRS, Laboratoire Interdisciplinaire Carnot de Bourgogne ICB UMR 6303, Dijon, France. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper explores Text-to-Knowledge Graph (T2KG) construction, assessing Zero-Shot Prompting, Few-Shot Prompting, and Fine-Tuning methods with Large Language Models. Through comprehensive experimentation with Llama2, Mistral, and Starling, we highlight the strengths of FT, emphasize dataset size's role, and introduce nuanced evaluation metrics. Promising perspectives include synonym-aware metric refinement, and data augmentation with Large Language Models. The study contributes valuable insights to KG construction methodologies, setting the stage for further advancements. 1
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Université Bourgogne Europe, CNRS, Laboratoire Interdisciplinaire Carnot de Bourgogne ICB UMR 6303, Dijon, France.
- DAVI The Humanizers, Puteaux, France.
Zitieren
APA
Ghanem, H., & Cruz, C. (2025). Fine-tuning or prompting on LLMs: evaluating knowledge graph construction task. Frontiers in Big Data, 8. https://doi.org/10.3389/fdata.2025.1505877
Vancouver
Ghanem H, Cruz C. Fine-tuning or prompting on LLMs: evaluating knowledge graph construction task. Frontiers in Big Data. 2025;8. doi:10.3389/fdata.2025.1505877
BibTeX
@article{Ghanem2025,
author = {Ghanem, Hussam and Cruz, Christophe},
title = {Fine-tuning or prompting on LLMs: evaluating knowledge graph construction task},
journal = {Frontiers in Big Data},
year = {2025},
volume = {8},
doi = {10.3389/fdata.2025.1505877}
}
EUVIMED