ChunkUIE: Chunked instruction-based unified information extraction
PLOS One · 27.06.2025 · 20 (6) · e0326764
DOI: 10.1371/journal.pone.0326764 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 27.06.2025. Verfasst von Wei Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: National Defense University, Beijing, China. Hauptthemen laut MEDLINE: Language, Linguistics, Information Storage and Retrieval. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large language models (LLMs) have demonstrated remarkable performance across various linguistic tasks. However, existing LLMs perform inadequately in information extraction tasks for both Chinese and English. Numerous studies attempt to enhance model performance by increasing the scale of training data. However, discrepancies in the number and type of schemas used during training and evaluation can harm model effectiveness. To tackle this challenge, we propose ChunkUIE, a unified information extraction model that supports Chinese and English. We design a chunked instruction construction strategy that randomly and reproducibly divides all schemas into chunks containing an identical number of schemas. This approach ensures that the union of schemas across all chunks encompasses all schemas. By limiting the number of schemas in each instruction, this strategy effectively addresses the performance degradation caused by inconsistencies in schema counts between training and evaluation. Additionally, we construct some challenging negative schemas using a predefined hard schema dictionary, which mitigates the model’s semantic confusion regarding similar schemas. Experimental results demonstrate that ChunkUIE enhances zero-shot performance in information extraction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- National Defense University, Beijing, China.
- State Key Laboratory of Geo-Information Engineering, Beijing, China.
- Beijing Gengtu Technology Co., Ltd., Beijing, China.
- School of Transportation, Southeast University, Nanjing, China.
ORCID-Profile: Wei Men
Zitieren
APA
Li, W., Liu, Y., Yang, Y., Zhang, T., & Men, W. (2025). ChunkUIE: Chunked instruction-based unified information extraction. PLOS One, 20(6), e0326764. https://doi.org/10.1371/journal.pone.0326764
Vancouver
Li W, Liu Y, Yang Y, Zhang T, Men W. ChunkUIE: Chunked instruction-based unified information extraction. PLOS One. 2025;20(6):e0326764. doi:10.1371/journal.pone.0326764
BibTeX
@article{Li2025,
author = {Li, Wei and Liu, Yingzhen and Yang, Yinling and Zhang, Ting and Men, Wei},
title = {ChunkUIE: Chunked instruction-based unified information extraction},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {6},
pages = {e0326764},
doi = {10.1371/journal.pone.0326764}
}
EUVIMED