EUVIMEDEUVIMED entdecken
Crossref

LLM-driven materials knowledge extraction: multimodal parsing, ontology, and agentic systems

Shuai Yang, Yimeng Wang, Qiong Tu, Nian Ran, Ying Lu

Journal of Materials Informatics · 31.07.2026 · 6 (3)

DOI: 10.20517/jmi.2026.38 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Materials Informatics, online erschienen am 31.07.2026. Verfasst von Shuai Yang und 4 weiteren Autor:innen. Die Arbeit nennt 147 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extracting reliable knowledge from unstructured materials literature remains a central bottleneck for data-driven and AI-enabled materials discovery. Large language models (LLMs) are reshaping this task by integrating multimodal document parsing, ontology-guided semantic grounding, structured extraction, and agentic verification into increasingly unified workflows. This review analyzes these developments through a Perception–Cognition–Action lens. At the perception layer, we examine how scientific document parsers, multimodal LLMs, table and chart readers, and optical chemical-structure-recognition systems convert visually rich papers into computable evidence. At the cognition layer, we discuss how ontologies and knowledge graphs constrain LLM outputs, support entity alignment, and reduce semantic ambiguity. At the action layer, we compare schema-based extraction, schema-free discovery, and agentic extraction as a control–coverage–autonomy spectrum rather than a simple succession of tools. We further argue that reliability is the decisive criterion for large-scale deployment, and synthesize failure modes, layered defenses, and evaluation protocols that connect source grounding, ontology constraints, physical verification, and human-in-the-loop review. By distinguishing demonstrated extraction capabilities from more speculative AI-scientist and self-driving-laboratory visions, this review provides a comparative and risk-aware account of how LLM-driven systems can produce evidence-linked, physically meaningful, and reusable materials knowledge.

Zitieren

APA

Yang, S., Wang, Y., Tu, Q., Ran, N., & Lu, Y. (2026). LLM-driven materials knowledge extraction: multimodal parsing, ontology, and agentic systems. Journal of Materials Informatics, 6(3). https://doi.org/10.20517/jmi.2026.38

Vancouver

Yang S, Wang Y, Tu Q, Ran N, Lu Y. LLM-driven materials knowledge extraction: multimodal parsing, ontology, and agentic systems. Journal of Materials Informatics. 2026;6(3). doi:10.20517/jmi.2026.38

BibTeX
@article{Yang2026,
  author = {Yang, Shuai and Wang, Yimeng and Tu, Qiong and Ran, Nian and Lu, Ying},
  title = {LLM-driven materials knowledge extraction: multimodal parsing, ontology, and agentic systems},
  journal = {Journal of Materials Informatics},
  year = {2026},
  volume = {6},
  number = {3},
  doi = {10.20517/jmi.2026.38}
}
Kostenlos starten →