Keywords
Graph Propagation
Reinforcement Signals
Concept Induction
Label Quality
Knowledge Validation
Abstract
Structured Knowledge Extraction is being reorganized around the joint demands of performance with evidence quality, resource limits, and transfer across settings. The present synthesis investigates turning heterogeneous observations and language into relations and concepts that remain traceable to evidence. Its analysis connects 2 focal papers with 13 independently retrieved publications validated against DOI-registration metadata. The analysis is organized around graph propagation, reinforcement signals, concept induction, label quality, and knowledge validation. A central precaution is not to treat published metrics as automatically comparable, the review compares task scope, modeling premises, and evaluation limits. Across the literature, the central lesson is that advances in structured knowledge extraction become credible when representation, objective, and evaluation protocol are evaluated together and when uncertainty about distribution shift is reported explicitly. This organization relates method selection to decision risk and exposes recurring transfer threats, and proposes a research agenda centered on auditable baselines, controlled perturbations, and replicable records.
References
Yang, R., & Gupta, R. (2025). Enhancing Multi-Modal Relation Extraction with Reinforcement Learning Guided Graph Diffusion Framework. In Proceedings of the 31st International Conference on Computational Linguistics (pp. 978-988).
Zhang, Z., Wu, Q., Xia, B., Sun, F., Hu, Z., Sun, Y., & Zhang, S. (2025). Automated Molecular Concept Generation and Labeling with Large Language Models. In Proceedings of the 31st International Conference on Computational Linguistics (pp. 6918-6936).
Liu, B., & Qi, G. (2025). LLM-CG: Large language model-enhanced constraint graph for distantly supervised relation extraction. Neurocomputing, 655, 131426. https://doi.org/10.1016/j.neucom.2025.131426
HE, L., WANG, R., DUAN, J., WANG, H., & LI, X. (2026). LLM-VGA: Large Language Model-Augmented Visual Generation with Hierarchical Bidirectional Alignment for Multimodal Relation Extraction. IEICE Transactions on Information and Systems. https://doi.org/10.1587/transinf.2025edp7173
Zheng, H., & Huang, X. (2026). Photorealistic Fire Scene Video Generation via Multimodal Large Language Model and Pre-Trained Video Diffusion Model. Computational Visual Media, 12(3), 841-848. https://doi.org/10.26599/cvm.2025.9450511
Aidynkyzy, A. (2026). FROM NAMED ENTITY RECOGNITION TO RELATION EXTRACTION: LARGE LANGUAGE MODEL ASSISTED CONSTRUCTION OF THE KAZAKH RELATION EXTRACTION DATASET. Вестник Академии гражданской авиации, 41(2). https://doi.org/10.53364/24138614_2026_41_2_13
He, W., Ma, H., Li, S., Dong, H., Zhang, H., & Feng, J. (2023). Using Augmented Small Multimodal Models to Guide Large Language Models for Multimodal Relation Extraction. Applied Sciences, 13(22), 12208. https://doi.org/10.3390/app132212208
Li, S., Sun, B., Li, S., & Yang, B. (2026). Multimodal large model driven pseudo labeling for unbiased scene graph generation. Neurocomputing, 664, 132170. https://doi.org/10.1016/j.neucom.2025.132170
Gui, H., Yang, Z., Harish, A. R., Ren, C., Yang, Y., & Li, M. (2025). GenPattern: dual-graph enhanced sewing pattern generation via multimodal large language model. Journal of Manufacturing Systems, 83, 822-838. https://doi.org/10.1016/j.jmsy.2025.11.005
Yang, L., Li, Y., Tan, J., & Mao, L. (2025). Research on risk decision-making generation method for water conservancy project based on multimodal knowledge graph and large language model. PLOS One, 20(8), e0330258. https://doi.org/10.1371/journal.pone.0330258
Zhao, W. (2026). Ceramic art design generation and aesthetic quality evaluation based on multimodal large language models and diffusion probabilistic framework. Scientific Reports, 16(1). https://doi.org/10.1038/s41598-026-55502-z
Park, J., Bae, M., Na, J., & Kim, H. J. (2026). Improving Large Molecular Language Model via Relation-aware Multimodal Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 899-907. https://doi.org/10.1609/aaai.v40i2.37058
Zhang, S., & Cheng, Q. (2026). User preference generation and recommendation of new energy vehicles based on diffusion model and multimodal knowledge graph. Information Sciences, 757, 123919. https://doi.org/10.1016/j.ins.2026.123919
Bhattacharya, M., Pal, S., Chatterjee, S., Lee, S. S., & Chakraborty, C. (2024). Large language model to multimodal large language model: A journey to shape the biological macromolecules to biological sciences and medicine. Molecular Therapy - Nucleic Acids, 35(3), 102255. https://doi.org/10.1016/j.omtn.2024.102255
Ren, R., Ma, J., & Luo, J. (2025). Large language model for patent concept generation. Advanced Engineering Informatics, 65, 103301. https://doi.org/10.1016/j.aei.2025.103301
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2026 Cameron Bailey, Patrick Freeman, Dylan Martin (Author)