EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GenForge: An LMM Agent Framework for Intelligent Knowledge Extraction from Nuclear Fuel Reprocessing Literature

Hengfei Wang, Ting Yu, Yuanzheng Xin, Zonghui Lu, Shuangjian Li, Yingting Luo, Guoan Ye, Helin Gong, Tao Zhu

Information · 03.05.2026 · 17 (5) · 441

DOI: 10.3390/info17050441 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 03.05.2026. Verfasst von Hengfei Wang und 8 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Young Talent Cultivation Fund of CIAE, SASTIND Stable Support Scientific Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nuclear Fuel Reprocessing literature contains critical experimental parameters, safety information, theoretical relations, and process data that are highly heterogeneous and subject to strict logical constraints. Manually interpreting complex charts and handling tedious database schema mappings imposes a high cognitive load on experts. Although existing Large Multimodal Models (LMMs) have demonstrated strong potential in information extraction, they often face engineering bottlenecks—such as poor structural compliance and a tendency to confuse entity logic—when dealing with domain databases containing complex foreign key constraints. To address this, we propose GenForge, a schema-aware extraction framework. By taking the target database schema as an explicit constraint, GenForge achieves automatic task decomposition and formatting self-correction via a “Generation–Execution–Reflection–Reforging” iterative loop. Additionally, a Local ID mechanism is introduced to ensure data lineage consistency. We evaluated GenForge on four internal evaluation corpora from nuclear fuel reprocessing literature, each aligned with a distinct database schema: Safety Event and Causal Context Extraction Schema, Property-Condition Data Extraction Schema, Model-Parameter Association Schema, and Process Topology and Stream Mapping Schema. On the independent test set, GenForge achieved 88.0% precision, 83.0% recall, and a 98.6% Schema Compliance Rate (SCR). These results indicate that GenForge, as an expert-assisted framework, reduces the need for manual JSON debugging and supports practical schema-constrained knowledge extraction under four schema-specific evaluation settings within the Nuclear Fuel Reprocessing domain.

Förderung

  • Young Talent Cultivation Fund of CIAE
  • SASTIND Stable Support Scientific Research Project

Zitieren

APA

Wang, H., Yu, T., Xin, Y., Lu, Z., Li, S., Luo, Y., Ye, G., Gong, H., & Zhu, T. (2026). GenForge: An LMM Agent Framework for Intelligent Knowledge Extraction from Nuclear Fuel Reprocessing Literature. Information, 17(5), 441. https://doi.org/10.3390/info17050441

Vancouver

Wang H, Yu T, Xin Y, Lu Z, Li S, Luo Y, et al. GenForge: An LMM Agent Framework for Intelligent Knowledge Extraction from Nuclear Fuel Reprocessing Literature. Information. 2026;17(5):441. doi:10.3390/info17050441

BibTeX
@article{Wang2026,
  author = {Wang, Hengfei and Yu, Ting and Xin, Yuanzheng and Lu, Zonghui and Li, Shuangjian and Luo, Yingting and Ye, Guoan and Gong, Helin and Zhu, Tao},
  title = {GenForge: An LMM Agent Framework for Intelligent Knowledge Extraction from Nuclear Fuel Reprocessing Literature},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {5},
  pages = {441},
  doi = {10.3390/info17050441}
}
Kostenlos starten →