UniDRE: Universal method for document-level relation extraction with knowledge retrieval and reasoning augmentation on small and large language models
Journal of King Saud University Computer and Information Sciences · 2026-12 · 38 (10)
DOI: 10.1007/s44443-026-01453-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 19.11.2026. Verfasst von Chengcheng Mai und 5 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Jiangsu Province Frontier Technology Research and Development Program, Open project of State Key Laboratory for Novel Software Technology, the National Natural Science Foundation of China.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Jiangsu Province Frontier Technology Research and Development Program
- Open project of State Key Laboratory for Novel Software Technology
- the National Natural Science Foundation of China
Zitieren
APA
Mai, C., Xie, T., Wang, Y., Wang, H., Ji, G., & Huang, Y. (2026). UniDRE: Universal method for document-level relation extraction with knowledge retrieval and reasoning augmentation on small and large language models. Journal of King Saud University Computer and Information Sciences, 38(10). https://doi.org/10.1007/s44443-026-01453-4
Vancouver
Mai C, Xie T, Wang Y, Wang H, Ji G, Huang Y. UniDRE: Universal method for document-level relation extraction with knowledge retrieval and reasoning augmentation on small and large language models. Journal of King Saud University Computer and Information Sciences. 2026;38(10). doi:10.1007/s44443-026-01453-4
BibTeX
@article{Mai2026,
author = {Mai, Chengcheng and Xie, Tongtong and Wang, Yuxiang and Wang, Hanxiang and Ji, Genlin and Huang, Yihua},
title = {UniDRE: Universal method for document-level relation extraction with knowledge retrieval and reasoning augmentation on small and large language models},
journal = {Journal of King Saud University Computer and Information Sciences},
year = {2026},
volume = {38},
number = {10},
doi = {10.1007/s44443-026-01453-4}
}
EUVIMED